diff --git a/README.md b/README.md index b3c2aa2..97b2984 100644 --- a/README.md +++ b/README.md @@ -117,384 +117,385 @@ Units denominated in USD. All prices can be located in `model_prices.json`. * Prices last updated Jan 30, 2024 from: https://openai.com/pricing and https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json -| | max_tokens | max_input_tokens | input_cost_per_token | output_cost_per_token | -|:--------------------------------------------------------------------------------------------|:-------------|:-------------------|:-----------------------|:------------------------| -| gpt-4 | 4,096 | 8,192 | $0.00003000 | $0.00006000 | -| gpt-4o | 4,096 | 128,000 | $0.00000500 | $0.00001500 | -| gpt-4o-2024-05-13 | 4,096 | 128,000 | $0.00000500 | $0.00001500 | -| gpt-4-turbo-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-0314 | 4,096 | 8,192 | $0.00003000 | $0.00006000 | -| gpt-4-0613 | 4,096 | 8,192 | $0.00003000 | $0.00006000 | -| gpt-4-32k | 4,096 | 32,768 | $0.00006000 | $0.00012000 | -| gpt-4-32k-0314 | 4,096 | 32,768 | $0.00006000 | $0.00012000 | -| gpt-4-32k-0613 | 4,096 | 32,768 | $0.00006000 | $0.00012000 | -| gpt-4-turbo | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-turbo-2024-04-09 | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-1106-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-0125-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-vision-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-1106-vision-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-3.5-turbo | 4,097 | 16,385 | $0.00000150 | $0.00000200 | -| gpt-3.5-turbo-0301 | 4,097 | 4,097 | $0.00000150 | $0.00000200 | -| gpt-3.5-turbo-0613 | 4,097 | 4,097 | $0.00000150 | $0.00000200 | -| gpt-3.5-turbo-1106 | 16,385 | 16,385 | $0.00000100 | $0.00000200 | -| gpt-3.5-turbo-0125 | 16,385 | 16,385 | $0.00000050 | $0.00000150 | -| gpt-3.5-turbo-16k | 16,385 | 16,385 | $0.00000300 | $0.00000400 | -| gpt-3.5-turbo-16k-0613 | 16,385 | 16,385 | $0.00000300 | $0.00000400 | -| ft:gpt-3.5-turbo | 4,097 | 4,097 | $0.00000300 | $0.00000600 | -| text-embedding-3-large | 8,191 | 8,191 | $0.00000013 | $0.00000000 | -| text-embedding-3-small | 8,191 | 8,191 | $0.00000002 | $0.00000000 | -| text-embedding-ada-002 | 8,191 | 8,191 | $0.00000010 | $0.00000000 | -| text-embedding-ada-002-v2 | 8,191 | 8,191 | $0.00000010 | $0.00000000 | -| text-moderation-stable | 32,768 | 32,768 | $0.00000000 | $0.00000000 | -| text-moderation-007 | 32,768 | 32,768 | $0.00000000 | $0.00000000 | -| text-moderation-latest | 32,768 | 32,768 | $0.00000000 | $0.00000000 | -| 256-x-256/dall-e-2 | nan | nan | -- | -- | -| 512-x-512/dall-e-2 | nan | nan | -- | -- | -| 1024-x-1024/dall-e-2 | nan | nan | -- | -- | -| hd/1024-x-1792/dall-e-3 | nan | nan | -- | -- | -| hd/1792-x-1024/dall-e-3 | nan | nan | -- | -- | -| hd/1024-x-1024/dall-e-3 | nan | nan | -- | -- | -| standard/1024-x-1792/dall-e-3 | nan | nan | -- | -- | -| standard/1792-x-1024/dall-e-3 | nan | nan | -- | -- | -| standard/1024-x-1024/dall-e-3 | nan | nan | -- | -- | -| whisper-1 | nan | nan | -- | -- | -| azure/whisper-1 | nan | nan | -- | -- | -| azure/gpt-4-turbo-2024-04-09 | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| azure/gpt-4-0125-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| azure/gpt-4-1106-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| azure/gpt-4-0613 | 4,096 | 8,192 | $0.00003000 | $0.00006000 | -| azure/gpt-4-32k-0613 | 4,096 | 32,768 | $0.00006000 | $0.00012000 | -| azure/gpt-4-32k | 4,096 | 32,768 | $0.00006000 | $0.00012000 | -| azure/gpt-4 | 4,096 | 8,192 | $0.00003000 | $0.00006000 | -| azure/gpt-4-turbo | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| azure/gpt-4-turbo-vision-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| azure/gpt-35-turbo-16k-0613 | 4,096 | 16,385 | $0.00000300 | $0.00000400 | -| azure/gpt-35-turbo-1106 | 4,096 | 16,384 | $0.00000150 | $0.00000200 | -| azure/gpt-35-turbo-0125 | 4,096 | 16,384 | $0.00000050 | $0.00000150 | -| azure/gpt-35-turbo-16k | 4,096 | 16,385 | $0.00000300 | $0.00000400 | -| azure/gpt-35-turbo | 4,096 | 4,097 | $0.00000150 | $0.00000200 | -| azure/gpt-3.5-turbo-instruct-0914 | 4,097 | 4,097 | $0.00000150 | $0.00000200 | -| azure/gpt-35-turbo-instruct | 4,097 | 4,097 | $0.00000150 | $0.00000200 | -| azure/mistral-large-latest | 32,000 | 32,000 | $0.00000800 | $0.00002400 | -| azure/mistral-large-2402 | 32,000 | 32,000 | $0.00000800 | $0.00002400 | -| azure/command-r-plus | 4,096 | 128,000 | $0.00000300 | $0.00001500 | -| azure/ada | 8,191 | 8,191 | $0.00000010 | $0.00000000 | -| azure/text-embedding-ada-002 | 8,191 | 8,191 | $0.00000010 | $0.00000000 | -| azure/text-embedding-3-large | 8,191 | 8,191 | $0.00000013 | $0.00000000 | -| azure/text-embedding-3-small | 8,191 | 8,191 | $0.00000002 | $0.00000000 | -| azure/standard/1024-x-1024/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/hd/1024-x-1024/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/standard/1024-x-1792/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/standard/1792-x-1024/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/hd/1024-x-1792/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/hd/1792-x-1024/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/standard/1024-x-1024/dall-e-2 | nan | nan | -- | $0.00000000 | -| babbage-002 | 16,384 | 16,384 | $0.00000040 | $0.00000040 | -| davinci-002 | 16,384 | 16,384 | $0.00000200 | $0.00000200 | -| gpt-3.5-turbo-instruct | 4,096 | 8,192 | $0.00000150 | $0.00000200 | -| gpt-3.5-turbo-instruct-0914 | 4,097 | 8,192 | $0.00000150 | $0.00000200 | -| claude-instant-1 | 8,191 | 100,000 | $0.00000163 | $0.00000551 | -| mistral/mistral-tiny | 8,191 | 32,000 | $0.00000015 | $0.00000046 | -| mistral/mistral-small | 8,191 | 32,000 | $0.00000200 | $0.00000600 | -| mistral/mistral-small-latest | 8,191 | 32,000 | $0.00000200 | $0.00000600 | -| mistral/mistral-medium | 8,191 | 32,000 | $0.00000270 | $0.00000810 | -| mistral/mistral-medium-latest | 8,191 | 32,000 | $0.00000270 | $0.00000810 | -| mistral/mistral-medium-2312 | 8,191 | 32,000 | $0.00000270 | $0.00000810 | -| mistral/mistral-large-latest | 8,191 | 32,000 | $0.00000800 | $0.00002400 | -| mistral/mistral-large-2402 | 8,191 | 32,000 | $0.00000800 | $0.00002400 | -| mistral/open-mixtral-8x7b | 8,191 | 32,000 | $0.00000200 | $0.00000600 | -| mistral/mistral-embed | 8,192 | 8,192 | $0.00000011 | -- | -| deepseek-chat | 4,096 | 32,000 | $0.00000014 | $0.00000028 | -| deepseek-coder | 4,096 | 16,000 | $0.00000014 | $0.00000028 | -| groq/llama2-70b-4096 | 4,096 | 4,096 | $0.00000070 | $0.00000080 | -| groq/llama3-8b-8192 | 8,192 | 8,192 | $0.00000010 | $0.00000010 | -| groq/llama3-70b-8192 | 8,192 | 8,192 | $0.00000064 | $0.00000080 | -| groq/mixtral-8x7b-32768 | 32,768 | 32,768 | $0.00000027 | $0.00000027 | -| groq/gemma-7b-it | 8,192 | 8,192 | $0.00000010 | $0.00000010 | -| claude-instant-1.2 | 8,191 | 100,000 | $0.00000016 | $0.00000055 | -| claude-2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| claude-2.1 | 8,191 | 200,000 | $0.00000800 | $0.00002400 | -| claude-3-haiku-20240307 | 4,096 | 200,000 | $0.00000025 | $0.00000125 | -| claude-3-opus-20240229 | 4,096 | 200,000 | $0.00001500 | $0.00007500 | -| claude-3-sonnet-20240229 | 4,096 | 200,000 | $0.00000300 | $0.00001500 | -| text-bison | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| text-bison@001 | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| text-unicorn | 1,024 | 8,192 | $0.00001000 | $0.00002800 | -| text-unicorn@001 | 1,024 | 8,192 | $0.00001000 | $0.00002800 | -| chat-bison | 4,096 | 8,192 | $0.00000012 | $0.00000012 | -| chat-bison@001 | 4,096 | 8,192 | $0.00000012 | $0.00000012 | -| chat-bison@002 | 4,096 | 8,192 | $0.00000012 | $0.00000012 | -| chat-bison-32k | 8,192 | 32,000 | $0.00000012 | $0.00000012 | -| code-bison | 1,024 | 6,144 | $0.00000012 | $0.00000012 | -| code-bison@001 | 1,024 | 6,144 | $0.00000012 | $0.00000012 | -| code-gecko@001 | 64 | 2,048 | $0.00000012 | $0.00000012 | -| code-gecko@002 | 64 | 2,048 | $0.00000012 | $0.00000012 | -| code-gecko | 64 | 2,048 | $0.00000012 | $0.00000012 | -| codechat-bison | 1,024 | 6,144 | $0.00000012 | $0.00000012 | -| codechat-bison@001 | 1,024 | 6,144 | $0.00000012 | $0.00000012 | -| codechat-bison-32k | 8,192 | 32,000 | $0.00000012 | $0.00000012 | -| gemini-pro | 8,192 | 32,760 | $0.00000025 | $0.00000050 | -| gemini-1.0-pro | 8,192 | 32,760 | $0.00000025 | $0.00000050 | -| gemini-1.0-pro-001 | 8,192 | 32,760 | $0.00000025 | $0.00000050 | -| gemini-1.0-pro-002 | 8,192 | 32,760 | $0.00000025 | $0.00000050 | -| gemini-1.5-pro | 8,192 | 1,000,000 | $0.00000063 | $0.00000188 | -| gemini-1.5-pro-preview-0215 | 8,192 | 1,000,000 | $0.00000063 | $0.00000188 | -| gemini-1.5-pro-preview-0409 | 8,192 | 1,000,000 | $0.00000063 | $0.00000188 | -| gemini-experimental | 8,192 | 1,000,000 | $0.00000000 | $0.00000000 | -| gemini-pro-vision | 2,048 | 16,384 | $0.00000025 | $0.00000050 | -| gemini-1.0-pro-vision | 2,048 | 16,384 | $0.00000025 | $0.00000050 | -| gemini-1.0-pro-vision-001 | 2,048 | 16,384 | $0.00000025 | $0.00000050 | -| vertex_ai/claude-3-sonnet@20240229 | 4,096 | 200,000 | $0.00000300 | $0.00001500 | -| vertex_ai/claude-3-haiku@20240307 | 4,096 | 200,000 | $0.00000025 | $0.00000125 | -| vertex_ai/claude-3-opus@20240229 | 4,096 | 200,000 | $0.00000150 | $0.00000750 | -| textembedding-gecko | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| textembedding-gecko-multilingual | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| textembedding-gecko-multilingual@001 | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| textembedding-gecko@001 | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| textembedding-gecko@003 | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| text-embedding-preview-0409 | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| text-multilingual-embedding-preview-0409 | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| palm/chat-bison | 4,096 | 8,192 | $0.00000012 | $0.00000012 | -| palm/chat-bison-001 | 4,096 | 8,192 | $0.00000012 | $0.00000012 | -| palm/text-bison | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| palm/text-bison-001 | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| palm/text-bison-safety-off | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| palm/text-bison-safety-recitation-off | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| gemini/gemini-pro | 8,192 | 32,760 | $0.00000000 | $0.00000000 | -| gemini/gemini-1.5-pro | 8,192 | 1,000,000 | $0.00000000 | $0.00000000 | -| gemini/gemini-1.5-pro-latest | 8,192 | 1,048,576 | $0.00000000 | $0.00000000 | -| gemini/gemini-pro-vision | 2,048 | 30,720 | $0.00000000 | $0.00000000 | -| command-r | 4,096 | 128,000 | $0.00000050 | $0.00000150 | -| command-light | 4,096 | 4,096 | $0.00001500 | $0.00001500 | -| command-r-plus | 4,096 | 128,000 | $0.00000300 | $0.00001500 | -| command-nightly | 4,096 | 4,096 | $0.00001500 | $0.00001500 | -| command | 4,096 | 4,096 | $0.00001500 | $0.00001500 | -| command-medium-beta | 4,096 | 4,096 | $0.00001500 | $0.00001500 | -| command-xlarge-beta | 4,096 | 4,096 | $0.00001500 | $0.00001500 | -| replicate/meta/llama-2-13b | 4,096 | 4,096 | $0.00000010 | $0.00000050 | -| replicate/meta/llama-2-13b-chat | 4,096 | 4,096 | $0.00000010 | $0.00000050 | -| replicate/meta/llama-2-70b | 4,096 | 4,096 | $0.00000065 | $0.00000275 | -| replicate/meta/llama-2-70b-chat | 4,096 | 4,096 | $0.00000065 | $0.00000275 | -| replicate/meta/llama-2-7b | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/meta/llama-2-7b-chat | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/meta/llama-3-70b | 4,096 | 4,096 | $0.00000065 | $0.00000275 | -| replicate/meta/llama-3-70b-instruct | 4,096 | 4,096 | $0.00000065 | $0.00000275 | -| replicate/meta/llama-3-8b | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/meta/llama-3-8b-instruct | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/mistralai/mistral-7b-v0.1 | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/mistralai/mistral-7b-instruct-v0.2 | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/mistralai/mixtral-8x7b-instruct-v0.1 | 4,096 | 4,096 | $0.00000030 | $0.00000100 | -| openrouter/microsoft/wizardlm-2-8x22b:nitro | 65,536 | nan | $0.00000100 | $0.00000100 | -| openrouter/google/gemini-pro-1.5 | 8,192 | 1,000,000 | $0.00000250 | $0.00000750 | -| openrouter/mistralai/mixtral-8x22b-instruct | 65,536 | nan | $0.00000065 | $0.00000065 | -| openrouter/cohere/command-r-plus | 128,000 | nan | $0.00000300 | $0.00001500 | -| openrouter/databricks/dbrx-instruct | 32,768 | nan | $0.00000060 | $0.00000060 | -| openrouter/anthropic/claude-3-haiku | 200,000 | nan | $0.00000025 | $0.00000125 | -| openrouter/anthropic/claude-3-sonnet | 200,000 | nan | $0.00000300 | $0.00001500 | -| openrouter/mistralai/mistral-large | 32,000 | nan | $0.00000800 | $0.00002400 | -| openrouter/cognitivecomputations/dolphin-mixtral-8x7b | 32,769 | nan | $0.00000050 | $0.00000050 | -| openrouter/google/gemini-pro-vision | 45,875 | nan | $0.00000012 | $0.00000038 | -| openrouter/fireworks/firellava-13b | 4,096 | nan | $0.00000020 | $0.00000020 | -| openrouter/meta-llama/llama-3-8b-instruct:free | 8,192 | nan | $0.00000000 | $0.00000000 | -| openrouter/meta-llama/llama-3-8b-instruct:extended | 16,384 | nan | $0.00000022 | $0.00000225 | -| openrouter/meta-llama/llama-3-70b-instruct:nitro | 8,192 | nan | $0.00000090 | $0.00000090 | -| openrouter/meta-llama/llama-3-70b-instruct | 8,192 | nan | $0.00000059 | $0.00000079 | -| openrouter/openai/gpt-4-vision-preview | 130,000 | nan | $0.00001000 | $0.00003000 | -| openrouter/openai/gpt-3.5-turbo | 4,095 | nan | $0.00000150 | $0.00000200 | -| openrouter/openai/gpt-3.5-turbo-16k | 16,383 | nan | $0.00000300 | $0.00000400 | -| openrouter/openai/gpt-4 | 8,192 | nan | $0.00003000 | $0.00006000 | -| openrouter/anthropic/claude-instant-v1 | 100,000 | nan | $0.00000163 | $0.00000551 | -| openrouter/anthropic/claude-2 | 100,000 | nan | $0.00001102 | $0.00003268 | -| openrouter/anthropic/claude-3-opus | 4,096 | 200,000 | $0.00001500 | $0.00007500 | -| openrouter/google/palm-2-chat-bison | 25,804 | nan | $0.00000050 | $0.00000050 | -| openrouter/google/palm-2-codechat-bison | 20,070 | nan | $0.00000050 | $0.00000050 | -| openrouter/meta-llama/llama-2-13b-chat | 4,096 | nan | $0.00000020 | $0.00000020 | -| openrouter/meta-llama/llama-2-70b-chat | 4,096 | nan | $0.00000150 | $0.00000150 | -| openrouter/meta-llama/codellama-34b-instruct | 8,096 | nan | $0.00000050 | $0.00000050 | -| openrouter/nousresearch/nous-hermes-llama2-13b | 4,096 | nan | $0.00000020 | $0.00000020 | -| openrouter/mancer/weaver | 8,000 | nan | $0.00000563 | $0.00000563 | -| openrouter/gryphe/mythomax-l2-13b | 8,192 | nan | $0.00000188 | $0.00000188 | -| openrouter/jondurbin/airoboros-l2-70b-2.1 | 4,096 | nan | $0.00001388 | $0.00001388 | -| openrouter/undi95/remm-slerp-l2-13b | 6,144 | nan | $0.00000188 | $0.00000188 | -| openrouter/pygmalionai/mythalion-13b | 4,096 | nan | $0.00000188 | $0.00000188 | -| openrouter/mistralai/mistral-7b-instruct | 8,192 | nan | $0.00000013 | $0.00000013 | -| openrouter/mistralai/mistral-7b-instruct:free | 8,192 | nan | $0.00000000 | $0.00000000 | -| j2-ultra | 8,192 | 8,192 | $0.00001500 | $0.00001500 | -| j2-mid | 8,192 | 8,192 | $0.00001000 | $0.00001000 | -| j2-light | 8,192 | 8,192 | $0.00000300 | $0.00000300 | -| dolphin | 16,384 | 16,384 | $0.00000050 | $0.00000050 | -| chatdolphin | 16,384 | 16,384 | $0.00000050 | $0.00000050 | -| luminous-base | 2,048 | nan | $0.00003000 | $0.00003300 | -| luminous-base-control | 2,048 | nan | $0.00003750 | $0.00004125 | -| luminous-extended | 2,048 | nan | $0.00004500 | $0.00004950 | -| luminous-extended-control | 2,048 | nan | $0.00005625 | $0.00006187 | -| luminous-supreme | 2,048 | nan | $0.00017500 | $0.00019250 | -| luminous-supreme-control | 2,048 | nan | $0.00021875 | $0.00024063 | -| ai21.j2-mid-v1 | 8,191 | 8,191 | $0.00001250 | $0.00001250 | -| ai21.j2-ultra-v1 | 8,191 | 8,191 | $0.00001880 | $0.00001880 | -| amazon.titan-text-lite-v1 | 4,000 | 42,000 | $0.00000030 | $0.00000040 | -| amazon.titan-text-express-v1 | 8,000 | 42,000 | $0.00000130 | $0.00000170 | -| amazon.titan-embed-text-v1 | 8,192 | 8,192 | $0.00000010 | $0.00000000 | -| amazon.titan-embed-text-v2:0 | 8,192 | 8,192 | $0.00000020 | $0.00000000 | -| mistral.mistral-7b-instruct-v0:2 | 8,191 | 32,000 | $0.00000015 | $0.00000020 | -| mistral.mixtral-8x7b-instruct-v0:1 | 8,191 | 32,000 | $0.00000045 | $0.00000070 | -| mistral.mistral-large-2402-v1:0 | 8,191 | 32,000 | $0.00000800 | $0.00002400 | -| bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1 | 8,191 | 32,000 | $0.00000045 | $0.00000070 | -| bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1 | 8,191 | 32,000 | $0.00000045 | $0.00000070 | -| bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1 | 8,191 | 32,000 | $0.00000059 | $0.00000091 | -| bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2 | 8,191 | 32,000 | $0.00000015 | $0.00000020 | -| bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2 | 8,191 | 32,000 | $0.00000015 | $0.00000020 | -| bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2 | 8,191 | 32,000 | $0.00000020 | $0.00000026 | -| bedrock/us-east-1/mistral.mistral-large-2402-v1:0 | 8,191 | 32,000 | $0.00000800 | $0.00002400 | -| bedrock/us-west-2/mistral.mistral-large-2402-v1:0 | 8,191 | 32,000 | $0.00000800 | $0.00002400 | -| bedrock/eu-west-3/mistral.mistral-large-2402-v1:0 | 8,191 | 32,000 | $0.00001040 | $0.00003120 | -| anthropic.claude-3-sonnet-20240229-v1:0 | 4,096 | 200,000 | $0.00000300 | $0.00001500 | -| anthropic.claude-3-haiku-20240307-v1:0 | 4,096 | 200,000 | $0.00000025 | $0.00000125 | -| anthropic.claude-3-opus-20240229-v1:0 | 4,096 | 200,000 | $0.00001500 | $0.00007500 | -| anthropic.claude-v1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-east-1/anthropic.claude-v1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-west-2/anthropic.claude-v1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/anthropic.claude-v1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/anthropic.claude-v1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/1-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/6-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/1-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/6-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| anthropic.claude-v2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-east-1/anthropic.claude-v2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-west-2/anthropic.claude-v2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/anthropic.claude-v2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/anthropic.claude-v2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/1-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/6-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/1-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/6-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| anthropic.claude-v2:1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-east-1/anthropic.claude-v2:1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-west-2/anthropic.claude-v2:1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/anthropic.claude-v2:1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/anthropic.claude-v2:1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| anthropic.claude-instant-v1 | 8,191 | 100,000 | $0.00000163 | $0.00000551 | -| bedrock/us-east-1/anthropic.claude-instant-v1 | 8,191 | 100,000 | $0.00000080 | $0.00000240 | -| bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/anthropic.claude-instant-v1 | 8,191 | 100,000 | $0.00000080 | $0.00000240 | -| bedrock/ap-northeast-1/anthropic.claude-instant-v1 | 8,191 | 100,000 | $0.00000223 | $0.00000755 | -| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/anthropic.claude-instant-v1 | 8,191 | 100,000 | $0.00000248 | $0.00000838 | -| bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| cohere.command-text-v14 | 4,096 | 4,096 | $0.00000150 | $0.00000200 | -| bedrock/*/1-month-commitment/cohere.command-text-v14 | 4,096 | 4,096 | -- | -- | -| bedrock/*/6-month-commitment/cohere.command-text-v14 | 4,096 | 4,096 | -- | -- | -| cohere.command-light-text-v14 | 4,096 | 4,096 | $0.00000030 | $0.00000060 | -| bedrock/*/1-month-commitment/cohere.command-light-text-v14 | 4,096 | 4,096 | -- | -- | -| bedrock/*/6-month-commitment/cohere.command-light-text-v14 | 4,096 | 4,096 | -- | -- | -| cohere.command-r-plus-v1:0 | 4,096 | 128,000 | $0.00000300 | $0.00001500 | -| cohere.command-r-v1:0 | 4,096 | 128,000 | $0.00000050 | $0.00000150 | -| cohere.embed-english-v3 | 512 | 512 | $0.00000010 | $0.00000000 | -| cohere.embed-multilingual-v3 | 512 | 512 | $0.00000010 | $0.00000000 | -| meta.llama2-13b-chat-v1 | 4,096 | 4,096 | $0.00000075 | $0.00000100 | -| meta.llama2-70b-chat-v1 | 4,096 | 4,096 | $0.00000195 | $0.00000256 | -| meta.llama3-8b-instruct-v1:0 | 8,192 | 8,192 | $0.00000040 | $0.00000060 | -| meta.llama3-70b-instruct-v1:0 | 8,192 | 8,192 | $0.00000265 | $0.00000350 | -| 512-x-512/50-steps/stability.stable-diffusion-xl-v0 | 77 | 77 | -- | -- | -| 512-x-512/max-steps/stability.stable-diffusion-xl-v0 | 77 | 77 | -- | -- | -| max-x-max/50-steps/stability.stable-diffusion-xl-v0 | 77 | 77 | -- | -- | -| max-x-max/max-steps/stability.stable-diffusion-xl-v0 | 77 | 77 | -- | -- | -| 1024-x-1024/50-steps/stability.stable-diffusion-xl-v1 | 77 | 77 | -- | -- | -| 1024-x-1024/max-steps/stability.stable-diffusion-xl-v1 | 77 | 77 | -- | -- | -| sagemaker/meta-textgeneration-llama-2-7b | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| sagemaker/meta-textgeneration-llama-2-7b-f | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| sagemaker/meta-textgeneration-llama-2-13b | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| sagemaker/meta-textgeneration-llama-2-13b-f | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| sagemaker/meta-textgeneration-llama-2-70b | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| sagemaker/meta-textgeneration-llama-2-70b-b-f | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| together-ai-up-to-3b | nan | nan | $0.00000010 | $0.00000010 | -| together-ai-3.1b-7b | nan | nan | $0.00000020 | $0.00000020 | -| together-ai-7.1b-20b | 1,000 | nan | $0.00000040 | $0.00000040 | -| together-ai-20.1b-40b | nan | nan | $0.00000080 | $0.00000080 | -| together-ai-40.1b-70b | nan | nan | $0.00000090 | $0.00000090 | -| together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1 | nan | nan | $0.00000060 | $0.00000060 | -| together_ai/mistralai/Mistral-7B-Instruct-v0.1 | nan | nan | -- | -- | -| together_ai/togethercomputer/CodeLlama-34b-Instruct | nan | nan | -- | -- | -| ollama/llama2 | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/llama2:13b | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/llama2:70b | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/llama2-uncensored | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/mistral | 8,192 | 8,192 | $0.00000000 | $0.00000000 | -| ollama/codellama | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/orca-mini | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/vicuna | 2,048 | 2,048 | $0.00000000 | $0.00000000 | -| deepinfra/lizpreciatior/lzlv_70b_fp16_hf | 4,096 | 4,096 | $0.00000070 | $0.00000090 | -| deepinfra/Gryphe/MythoMax-L2-13b | 4,096 | 4,096 | $0.00000022 | $0.00000022 | -| deepinfra/mistralai/Mistral-7B-Instruct-v0.1 | 8,191 | 32,768 | $0.00000013 | $0.00000013 | -| deepinfra/meta-llama/Llama-2-70b-chat-hf | 4,096 | 4,096 | $0.00000070 | $0.00000090 | -| deepinfra/cognitivecomputations/dolphin-2.6-mixtral-8x7b | 8,191 | 32,768 | $0.00000027 | $0.00000027 | -| deepinfra/codellama/CodeLlama-34b-Instruct-hf | 4,096 | 4,096 | $0.00000060 | $0.00000060 | -| deepinfra/deepinfra/mixtral | 4,096 | 32,000 | $0.00000027 | $0.00000027 | -| deepinfra/Phind/Phind-CodeLlama-34B-v2 | 4,096 | 16,384 | $0.00000060 | $0.00000060 | -| deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1 | 8,191 | 32,768 | $0.00000027 | $0.00000027 | -| deepinfra/deepinfra/airoboros-70b | 4,096 | 4,096 | $0.00000070 | $0.00000090 | -| deepinfra/01-ai/Yi-34B-Chat | 4,096 | 4,096 | $0.00000060 | $0.00000060 | -| deepinfra/01-ai/Yi-6B-200K | 4,096 | 200,000 | $0.00000013 | $0.00000013 | -| deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1 | 4,096 | 4,096 | $0.00000070 | $0.00000090 | -| deepinfra/meta-llama/Llama-2-13b-chat-hf | 4,096 | 4,096 | $0.00000022 | $0.00000022 | -| deepinfra/amazon/MistralLite | 8,191 | 32,768 | $0.00000020 | $0.00000020 | -| deepinfra/meta-llama/Llama-2-7b-chat-hf | 4,096 | 4,096 | $0.00000013 | $0.00000013 | -| deepinfra/01-ai/Yi-34B-200K | 4,096 | 200,000 | $0.00000060 | $0.00000060 | -| deepinfra/openchat/openchat_3.5 | 4,096 | 4,096 | $0.00000013 | $0.00000013 | -| perplexity/codellama-34b-instruct | 16,384 | 16,384 | $0.00000035 | $0.00000140 | -| perplexity/codellama-70b-instruct | 16,384 | 16,384 | $0.00000070 | $0.00000280 | -| perplexity/pplx-7b-chat | 8,192 | 8,192 | $0.00000007 | $0.00000028 | -| perplexity/pplx-70b-chat | 4,096 | 4,096 | $0.00000070 | $0.00000280 | -| perplexity/pplx-7b-online | 4,096 | 4,096 | $0.00000000 | $0.00000028 | -| perplexity/pplx-70b-online | 4,096 | 4,096 | $0.00000000 | $0.00000280 | -| perplexity/llama-2-70b-chat | 4,096 | 4,096 | $0.00000070 | $0.00000280 | -| perplexity/mistral-7b-instruct | 4,096 | 4,096 | $0.00000007 | $0.00000028 | -| perplexity/mixtral-8x7b-instruct | 4,096 | 4,096 | $0.00000007 | $0.00000028 | -| perplexity/sonar-small-chat | 16,384 | 16,384 | $0.00000007 | $0.00000028 | -| perplexity/sonar-small-online | 12,000 | 12,000 | $0.00000000 | $0.00000028 | -| perplexity/sonar-medium-chat | 16,384 | 16,384 | $0.00000060 | $0.00000180 | -| perplexity/sonar-medium-online | 12,000 | 12,000 | $0.00000000 | $0.00000180 | -| anyscale/mistralai/Mistral-7B-Instruct-v0.1 | 16,384 | 16,384 | $0.00000015 | $0.00000015 | -| anyscale/Mixtral-8x7B-Instruct-v0.1 | 16,384 | 16,384 | $0.00000015 | $0.00000015 | -| anyscale/HuggingFaceH4/zephyr-7b-beta | 16,384 | 16,384 | $0.00000015 | $0.00000015 | -| anyscale/meta-llama/Llama-2-7b-chat-hf | 4,096 | 4,096 | $0.00000015 | $0.00000015 | -| anyscale/meta-llama/Llama-2-13b-chat-hf | 4,096 | 4,096 | $0.00000025 | $0.00000025 | -| anyscale/meta-llama/Llama-2-70b-chat-hf | 4,096 | 4,096 | $0.00000100 | $0.00000100 | -| anyscale/codellama/CodeLlama-34b-Instruct-hf | 4,096 | 4,096 | $0.00000100 | $0.00000100 | -| cloudflare/@cf/meta/llama-2-7b-chat-fp16 | 3,072 | 3,072 | $0.00000192 | $0.00000192 | -| cloudflare/@cf/meta/llama-2-7b-chat-int8 | 2,048 | 2,048 | $0.00000192 | $0.00000192 | -| cloudflare/@cf/mistral/mistral-7b-instruct-v0.1 | 8,192 | 8,192 | $0.00000192 | $0.00000192 | -| cloudflare/@hf/thebloke/codellama-7b-instruct-awq | 4,096 | 4,096 | $0.00000192 | $0.00000192 | -| voyage/voyage-01 | 4,096 | 4,096 | $0.00000010 | $0.00000000 | -| voyage/voyage-lite-01 | 4,096 | 4,096 | $0.00000010 | $0.00000000 | -| voyage/voyage-large-2 | 16,000 | 16,000 | $0.00000012 | $0.00000000 | -| voyage/voyage-law-2 | 16,000 | 16,000 | $0.00000012 | $0.00000000 | -| voyage/voyage-code-2 | 16,000 | 16,000 | $0.00000012 | $0.00000000 | -| voyage/voyage-2 | 4,000 | 4,000 | $0.00000010 | $0.00000000 | -| voyage/voyage-lite-02-instruct | 4,000 | 4,000 | $0.00000010 | $0.00000000 | +| Model Name | Prompt Cost (USD) | Completion Cost (USD) | Max Prompt Tokens | Max Output Tokens | +|:--------------------------------------------------------------------------------------------|:--------------------|:------------------------|:--------------------|--------------------:| +| gpt-4 | $0.00003000 | $0.00006000 | 8,192 | 4096 | +| gpt-4o | $0.00000500 | $0.00001500 | 128,000 | 4096 | +| gpt-4o-2024-05-13 | $0.00000500 | $0.00001500 | 128,000 | 4096 | +| gpt-4-turbo-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-0314 | $0.00003000 | $0.00006000 | 8,192 | 4096 | +| gpt-4-0613 | $0.00003000 | $0.00006000 | 8,192 | 4096 | +| gpt-4-32k | $0.00006000 | $0.00012000 | 32,768 | 4096 | +| gpt-4-32k-0314 | $0.00006000 | $0.00012000 | 32,768 | 4096 | +| gpt-4-32k-0613 | $0.00006000 | $0.00012000 | 32,768 | 4096 | +| gpt-4-turbo | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-turbo-2024-04-09 | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-1106-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-0125-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-vision-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-1106-vision-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-3.5-turbo | $0.00000150 | $0.00000200 | 16,385 | 4096 | +| gpt-3.5-turbo-0301 | $0.00000150 | $0.00000200 | 4,097 | 4096 | +| gpt-3.5-turbo-0613 | $0.00000150 | $0.00000200 | 4,097 | 4096 | +| gpt-3.5-turbo-1106 | $0.00000100 | $0.00000200 | 16,385 | 4096 | +| gpt-3.5-turbo-0125 | $0.00000050 | $0.00000150 | 16,385 | 4096 | +| gpt-3.5-turbo-16k | $0.00000300 | $0.00000400 | 16,385 | 4096 | +| gpt-3.5-turbo-16k-0613 | $0.00000300 | $0.00000400 | 16,385 | 4096 | +| ft:gpt-3.5-turbo | $0.00000300 | $0.00000600 | 4,097 | 4096 | +| text-embedding-3-large | $0.00000013 | $0.00000000 | 8,191 | nan | +| text-embedding-3-small | $0.00000002 | $0.00000000 | 8,191 | nan | +| text-embedding-ada-002 | $0.00000010 | $0.00000000 | 8,191 | nan | +| text-embedding-ada-002-v2 | $0.00000010 | $0.00000000 | 8,191 | nan | +| text-moderation-stable | $0.00000000 | $0.00000000 | 32,768 | 0 | +| text-moderation-007 | $0.00000000 | $0.00000000 | 32,768 | 0 | +| text-moderation-latest | $0.00000000 | $0.00000000 | 32,768 | 0 | +| 256-x-256/dall-e-2 | -- | -- | nan | nan | +| 512-x-512/dall-e-2 | -- | -- | nan | nan | +| 1024-x-1024/dall-e-2 | -- | -- | nan | nan | +| hd/1024-x-1792/dall-e-3 | -- | -- | nan | nan | +| hd/1792-x-1024/dall-e-3 | -- | -- | nan | nan | +| hd/1024-x-1024/dall-e-3 | -- | -- | nan | nan | +| standard/1024-x-1792/dall-e-3 | -- | -- | nan | nan | +| standard/1792-x-1024/dall-e-3 | -- | -- | nan | nan | +| standard/1024-x-1024/dall-e-3 | -- | -- | nan | nan | +| whisper-1 | -- | -- | nan | nan | +| azure/whisper-1 | -- | -- | nan | nan | +| azure/gpt-4-turbo-2024-04-09 | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| azure/gpt-4-0125-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| azure/gpt-4-1106-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| azure/gpt-4-0613 | $0.00003000 | $0.00006000 | 8,192 | 4096 | +| azure/gpt-4-32k-0613 | $0.00006000 | $0.00012000 | 32,768 | 4096 | +| azure/gpt-4-32k | $0.00006000 | $0.00012000 | 32,768 | 4096 | +| azure/gpt-4 | $0.00003000 | $0.00006000 | 8,192 | 4096 | +| azure/gpt-4-turbo | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| azure/gpt-4-turbo-vision-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| azure/gpt-35-turbo-16k-0613 | $0.00000300 | $0.00000400 | 16,385 | 4096 | +| azure/gpt-35-turbo-1106 | $0.00000150 | $0.00000200 | 16,384 | 4096 | +| azure/gpt-35-turbo-0125 | $0.00000050 | $0.00000150 | 16,384 | 4096 | +| azure/gpt-35-turbo-16k | $0.00000300 | $0.00000400 | 16,385 | 4096 | +| azure/gpt-35-turbo | $0.00000150 | $0.00000200 | 4,097 | 4096 | +| azure/gpt-3.5-turbo-instruct-0914 | $0.00000150 | $0.00000200 | 4,097 | nan | +| azure/gpt-35-turbo-instruct | $0.00000150 | $0.00000200 | 4,097 | nan | +| azure/mistral-large-latest | $0.00000800 | $0.00002400 | 32,000 | nan | +| azure/mistral-large-2402 | $0.00000800 | $0.00002400 | 32,000 | nan | +| azure/command-r-plus | $0.00000300 | $0.00001500 | 128,000 | 4096 | +| azure/ada | $0.00000010 | $0.00000000 | 8,191 | nan | +| azure/text-embedding-ada-002 | $0.00000010 | $0.00000000 | 8,191 | nan | +| azure/text-embedding-3-large | $0.00000013 | $0.00000000 | 8,191 | nan | +| azure/text-embedding-3-small | $0.00000002 | $0.00000000 | 8,191 | nan | +| azure/standard/1024-x-1024/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/hd/1024-x-1024/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/standard/1024-x-1792/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/standard/1792-x-1024/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/hd/1024-x-1792/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/hd/1792-x-1024/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/standard/1024-x-1024/dall-e-2 | -- | $0.00000000 | nan | nan | +| babbage-002 | $0.00000040 | $0.00000040 | 16,384 | 4096 | +| davinci-002 | $0.00000200 | $0.00000200 | 16,384 | 4096 | +| gpt-3.5-turbo-instruct | $0.00000150 | $0.00000200 | 8,192 | 4096 | +| gpt-3.5-turbo-instruct-0914 | $0.00000150 | $0.00000200 | 8,192 | 4097 | +| claude-instant-1 | $0.00000163 | $0.00000551 | 100,000 | 8191 | +| mistral/mistral-tiny | $0.00000015 | $0.00000046 | 32,000 | 8191 | +| mistral/mistral-small | $0.00000200 | $0.00000600 | 32,000 | 8191 | +| mistral/mistral-small-latest | $0.00000200 | $0.00000600 | 32,000 | 8191 | +| mistral/mistral-medium | $0.00000270 | $0.00000810 | 32,000 | 8191 | +| mistral/mistral-medium-latest | $0.00000270 | $0.00000810 | 32,000 | 8191 | +| mistral/mistral-medium-2312 | $0.00000270 | $0.00000810 | 32,000 | 8191 | +| mistral/mistral-large-latest | $0.00000800 | $0.00002400 | 32,000 | 8191 | +| mistral/mistral-large-2402 | $0.00000800 | $0.00002400 | 32,000 | 8191 | +| mistral/open-mixtral-8x7b | $0.00000200 | $0.00000600 | 32,000 | 8191 | +| mistral/mistral-embed | $0.00000011 | -- | 8,192 | nan | +| deepseek-chat | $0.00000014 | $0.00000028 | 32,000 | 4096 | +| deepseek-coder | $0.00000014 | $0.00000028 | 16,000 | 4096 | +| groq/llama2-70b-4096 | $0.00000070 | $0.00000080 | 4,096 | 4096 | +| groq/llama3-8b-8192 | $0.00000010 | $0.00000010 | 8,192 | 8192 | +| groq/llama3-70b-8192 | $0.00000064 | $0.00000080 | 8,192 | 8192 | +| groq/mixtral-8x7b-32768 | $0.00000027 | $0.00000027 | 32,768 | 32768 | +| groq/gemma-7b-it | $0.00000010 | $0.00000010 | 8,192 | 8192 | +| claude-instant-1.2 | $0.00000016 | $0.00000055 | 100,000 | 8191 | +| claude-2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| claude-2.1 | $0.00000800 | $0.00002400 | 200,000 | 8191 | +| claude-3-haiku-20240307 | $0.00000025 | $0.00000125 | 200,000 | 4096 | +| claude-3-opus-20240229 | $0.00001500 | $0.00007500 | 200,000 | 4096 | +| claude-3-sonnet-20240229 | $0.00000300 | $0.00001500 | 200,000 | 4096 | +| text-bison | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| text-bison@001 | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| text-unicorn | $0.00001000 | $0.00002800 | 8,192 | 1024 | +| text-unicorn@001 | $0.00001000 | $0.00002800 | 8,192 | 1024 | +| chat-bison | $0.00000012 | $0.00000012 | 8,192 | 4096 | +| chat-bison@001 | $0.00000012 | $0.00000012 | 8,192 | 4096 | +| chat-bison@002 | $0.00000012 | $0.00000012 | 8,192 | 4096 | +| chat-bison-32k | $0.00000012 | $0.00000012 | 32,000 | 8192 | +| code-bison | $0.00000012 | $0.00000012 | 6,144 | 1024 | +| code-bison@001 | $0.00000012 | $0.00000012 | 6,144 | 1024 | +| code-gecko@001 | $0.00000012 | $0.00000012 | 2,048 | 64 | +| code-gecko@002 | $0.00000012 | $0.00000012 | 2,048 | 64 | +| code-gecko | $0.00000012 | $0.00000012 | 2,048 | 64 | +| codechat-bison | $0.00000012 | $0.00000012 | 6,144 | 1024 | +| codechat-bison@001 | $0.00000012 | $0.00000012 | 6,144 | 1024 | +| codechat-bison-32k | $0.00000012 | $0.00000012 | 32,000 | 8192 | +| gemini-pro | $0.00000025 | $0.00000050 | 32,760 | 8192 | +| gemini-1.0-pro | $0.00000025 | $0.00000050 | 32,760 | 8192 | +| gemini-1.0-pro-001 | $0.00000025 | $0.00000050 | 32,760 | 8192 | +| gemini-1.0-pro-002 | $0.00000025 | $0.00000050 | 32,760 | 8192 | +| gemini-1.5-pro | $0.00000063 | $0.00000188 | 1,000,000 | 8192 | +| gemini-1.5-pro-preview-0215 | $0.00000063 | $0.00000188 | 1,000,000 | 8192 | +| gemini-1.5-pro-preview-0409 | $0.00000063 | $0.00000188 | 1,000,000 | 8192 | +| gemini-experimental | $0.00000000 | $0.00000000 | 1,000,000 | 8192 | +| gemini-pro-vision | $0.00000025 | $0.00000050 | 16,384 | 2048 | +| gemini-1.0-pro-vision | $0.00000025 | $0.00000050 | 16,384 | 2048 | +| gemini-1.0-pro-vision-001 | $0.00000025 | $0.00000050 | 16,384 | 2048 | +| vertex_ai/claude-3-sonnet@20240229 | $0.00000300 | $0.00001500 | 200,000 | 4096 | +| vertex_ai/claude-3-haiku@20240307 | $0.00000025 | $0.00000125 | 200,000 | 4096 | +| vertex_ai/claude-3-opus@20240229 | $0.00000150 | $0.00000750 | 200,000 | 4096 | +| textembedding-gecko | $0.00000001 | $0.00000000 | 3,072 | nan | +| textembedding-gecko-multilingual | $0.00000001 | $0.00000000 | 3,072 | nan | +| textembedding-gecko-multilingual@001 | $0.00000001 | $0.00000000 | 3,072 | nan | +| textembedding-gecko@001 | $0.00000001 | $0.00000000 | 3,072 | nan | +| textembedding-gecko@003 | $0.00000001 | $0.00000000 | 3,072 | nan | +| text-embedding-preview-0409 | $0.00000001 | $0.00000000 | 3,072 | nan | +| text-multilingual-embedding-preview-0409 | $0.00000001 | $0.00000000 | 3,072 | nan | +| palm/chat-bison | $0.00000012 | $0.00000012 | 8,192 | 4096 | +| palm/chat-bison-001 | $0.00000012 | $0.00000012 | 8,192 | 4096 | +| palm/text-bison | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| palm/text-bison-001 | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| palm/text-bison-safety-off | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| palm/text-bison-safety-recitation-off | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| gemini/gemini-pro | $0.00000000 | $0.00000000 | 32,760 | 8192 | +| gemini/gemini-1.5-pro | $0.00000000 | $0.00000000 | 1,000,000 | 8192 | +| gemini/gemini-1.5-pro-latest | $0.00000000 | $0.00000000 | 1,048,576 | 8192 | +| gemini/gemini-pro-vision | $0.00000000 | $0.00000000 | 30,720 | 2048 | +| command-r | $0.00000050 | $0.00000150 | 128,000 | 4096 | +| command-light | $0.00001500 | $0.00001500 | 4,096 | 4096 | +| command-r-plus | $0.00000300 | $0.00001500 | 128,000 | 4096 | +| command-nightly | $0.00001500 | $0.00001500 | 4,096 | 4096 | +| command | $0.00001500 | $0.00001500 | 4,096 | 4096 | +| command-medium-beta | $0.00001500 | $0.00001500 | 4,096 | 4096 | +| command-xlarge-beta | $0.00001500 | $0.00001500 | 4,096 | 4096 | +| replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1 | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| replicate/meta/llama-2-13b | $0.00000010 | $0.00000050 | 4,096 | 4096 | +| replicate/meta/llama-2-13b-chat | $0.00000010 | $0.00000050 | 4,096 | 4096 | +| replicate/meta/llama-2-70b | $0.00000065 | $0.00000275 | 4,096 | 4096 | +| replicate/meta/llama-2-70b-chat | $0.00000065 | $0.00000275 | 4,096 | 4096 | +| replicate/meta/llama-2-7b | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/meta/llama-2-7b-chat | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/meta/llama-3-70b | $0.00000065 | $0.00000275 | 4,096 | 4096 | +| replicate/meta/llama-3-70b-instruct | $0.00000065 | $0.00000275 | 4,096 | 4096 | +| replicate/meta/llama-3-8b | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/meta/llama-3-8b-instruct | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/mistralai/mistral-7b-v0.1 | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/mistralai/mistral-7b-instruct-v0.2 | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/mistralai/mixtral-8x7b-instruct-v0.1 | $0.00000030 | $0.00000100 | 4,096 | 4096 | +| openrouter/microsoft/wizardlm-2-8x22b:nitro | $0.00000100 | $0.00000100 | nan | nan | +| openrouter/google/gemini-pro-1.5 | $0.00000250 | $0.00000750 | 1,000,000 | 8192 | +| openrouter/mistralai/mixtral-8x22b-instruct | $0.00000065 | $0.00000065 | nan | nan | +| openrouter/cohere/command-r-plus | $0.00000300 | $0.00001500 | nan | nan | +| openrouter/databricks/dbrx-instruct | $0.00000060 | $0.00000060 | nan | nan | +| openrouter/anthropic/claude-3-haiku | $0.00000025 | $0.00000125 | nan | nan | +| openrouter/anthropic/claude-3-sonnet | $0.00000300 | $0.00001500 | nan | nan | +| openrouter/mistralai/mistral-large | $0.00000800 | $0.00002400 | nan | nan | +| openrouter/cognitivecomputations/dolphin-mixtral-8x7b | $0.00000050 | $0.00000050 | nan | nan | +| openrouter/google/gemini-pro-vision | $0.00000012 | $0.00000038 | nan | nan | +| openrouter/fireworks/firellava-13b | $0.00000020 | $0.00000020 | nan | nan | +| openrouter/meta-llama/llama-3-8b-instruct:free | $0.00000000 | $0.00000000 | nan | nan | +| openrouter/meta-llama/llama-3-8b-instruct:extended | $0.00000022 | $0.00000225 | nan | nan | +| openrouter/meta-llama/llama-3-70b-instruct:nitro | $0.00000090 | $0.00000090 | nan | nan | +| openrouter/meta-llama/llama-3-70b-instruct | $0.00000059 | $0.00000079 | nan | nan | +| openrouter/openai/gpt-4-vision-preview | $0.00001000 | $0.00003000 | nan | nan | +| openrouter/openai/gpt-3.5-turbo | $0.00000150 | $0.00000200 | nan | nan | +| openrouter/openai/gpt-3.5-turbo-16k | $0.00000300 | $0.00000400 | nan | nan | +| openrouter/openai/gpt-4 | $0.00003000 | $0.00006000 | nan | nan | +| openrouter/anthropic/claude-instant-v1 | $0.00000163 | $0.00000551 | nan | 8191 | +| openrouter/anthropic/claude-2 | $0.00001102 | $0.00003268 | nan | 8191 | +| openrouter/anthropic/claude-3-opus | $0.00001500 | $0.00007500 | 200,000 | 4096 | +| openrouter/google/palm-2-chat-bison | $0.00000050 | $0.00000050 | nan | nan | +| openrouter/google/palm-2-codechat-bison | $0.00000050 | $0.00000050 | nan | nan | +| openrouter/meta-llama/llama-2-13b-chat | $0.00000020 | $0.00000020 | nan | nan | +| openrouter/meta-llama/llama-2-70b-chat | $0.00000150 | $0.00000150 | nan | nan | +| openrouter/meta-llama/codellama-34b-instruct | $0.00000050 | $0.00000050 | nan | nan | +| openrouter/nousresearch/nous-hermes-llama2-13b | $0.00000020 | $0.00000020 | nan | nan | +| openrouter/mancer/weaver | $0.00000563 | $0.00000563 | nan | nan | +| openrouter/gryphe/mythomax-l2-13b | $0.00000188 | $0.00000188 | nan | nan | +| openrouter/jondurbin/airoboros-l2-70b-2.1 | $0.00001388 | $0.00001388 | nan | nan | +| openrouter/undi95/remm-slerp-l2-13b | $0.00000188 | $0.00000188 | nan | nan | +| openrouter/pygmalionai/mythalion-13b | $0.00000188 | $0.00000188 | nan | nan | +| openrouter/mistralai/mistral-7b-instruct | $0.00000013 | $0.00000013 | nan | nan | +| openrouter/mistralai/mistral-7b-instruct:free | $0.00000000 | $0.00000000 | nan | nan | +| j2-ultra | $0.00001500 | $0.00001500 | 8,192 | 8192 | +| j2-mid | $0.00001000 | $0.00001000 | 8,192 | 8192 | +| j2-light | $0.00000300 | $0.00000300 | 8,192 | 8192 | +| dolphin | $0.00000050 | $0.00000050 | 16,384 | 16384 | +| chatdolphin | $0.00000050 | $0.00000050 | 16,384 | 16384 | +| luminous-base | $0.00003000 | $0.00003300 | nan | nan | +| luminous-base-control | $0.00003750 | $0.00004125 | nan | nan | +| luminous-extended | $0.00004500 | $0.00004950 | nan | nan | +| luminous-extended-control | $0.00005625 | $0.00006187 | nan | nan | +| luminous-supreme | $0.00017500 | $0.00019250 | nan | nan | +| luminous-supreme-control | $0.00021875 | $0.00024063 | nan | nan | +| ai21.j2-mid-v1 | $0.00001250 | $0.00001250 | 8,191 | 8191 | +| ai21.j2-ultra-v1 | $0.00001880 | $0.00001880 | 8,191 | 8191 | +| amazon.titan-text-lite-v1 | $0.00000030 | $0.00000040 | 42,000 | 4000 | +| amazon.titan-text-express-v1 | $0.00000130 | $0.00000170 | 42,000 | 8000 | +| amazon.titan-embed-text-v1 | $0.00000010 | $0.00000000 | 8,192 | nan | +| amazon.titan-embed-text-v2:0 | $0.00000020 | $0.00000000 | 8,192 | nan | +| mistral.mistral-7b-instruct-v0:2 | $0.00000015 | $0.00000020 | 32,000 | 8191 | +| mistral.mixtral-8x7b-instruct-v0:1 | $0.00000045 | $0.00000070 | 32,000 | 8191 | +| mistral.mistral-large-2402-v1:0 | $0.00000800 | $0.00002400 | 32,000 | 8191 | +| bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1 | $0.00000045 | $0.00000070 | 32,000 | 8191 | +| bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1 | $0.00000045 | $0.00000070 | 32,000 | 8191 | +| bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1 | $0.00000059 | $0.00000091 | 32,000 | 8191 | +| bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2 | $0.00000015 | $0.00000020 | 32,000 | 8191 | +| bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2 | $0.00000015 | $0.00000020 | 32,000 | 8191 | +| bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2 | $0.00000020 | $0.00000026 | 32,000 | 8191 | +| bedrock/us-east-1/mistral.mistral-large-2402-v1:0 | $0.00000800 | $0.00002400 | 32,000 | 8191 | +| bedrock/us-west-2/mistral.mistral-large-2402-v1:0 | $0.00000800 | $0.00002400 | 32,000 | 8191 | +| bedrock/eu-west-3/mistral.mistral-large-2402-v1:0 | $0.00001040 | $0.00003120 | 32,000 | 8191 | +| anthropic.claude-3-sonnet-20240229-v1:0 | $0.00000300 | $0.00001500 | 200,000 | 4096 | +| anthropic.claude-3-haiku-20240307-v1:0 | $0.00000025 | $0.00000125 | 200,000 | 4096 | +| anthropic.claude-3-opus-20240229-v1:0 | $0.00001500 | $0.00007500 | 200,000 | 4096 | +| anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-east-1/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-west-2/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-east-1/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-west-2/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-east-1/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-west-2/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| anthropic.claude-instant-v1 | $0.00000163 | $0.00000551 | 100,000 | 8191 | +| bedrock/us-east-1/anthropic.claude-instant-v1 | $0.00000080 | $0.00000240 | 100,000 | 8191 | +| bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/anthropic.claude-instant-v1 | $0.00000080 | $0.00000240 | 100,000 | 8191 | +| bedrock/ap-northeast-1/anthropic.claude-instant-v1 | $0.00000223 | $0.00000755 | 100,000 | 8191 | +| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/anthropic.claude-instant-v1 | $0.00000248 | $0.00000838 | 100,000 | 8191 | +| bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| cohere.command-text-v14 | $0.00000150 | $0.00000200 | 4,096 | 4096 | +| bedrock/*/1-month-commitment/cohere.command-text-v14 | -- | -- | 4,096 | 4096 | +| bedrock/*/6-month-commitment/cohere.command-text-v14 | -- | -- | 4,096 | 4096 | +| cohere.command-light-text-v14 | $0.00000030 | $0.00000060 | 4,096 | 4096 | +| bedrock/*/1-month-commitment/cohere.command-light-text-v14 | -- | -- | 4,096 | 4096 | +| bedrock/*/6-month-commitment/cohere.command-light-text-v14 | -- | -- | 4,096 | 4096 | +| cohere.command-r-plus-v1:0 | $0.00000300 | $0.00001500 | 128,000 | 4096 | +| cohere.command-r-v1:0 | $0.00000050 | $0.00000150 | 128,000 | 4096 | +| cohere.embed-english-v3 | $0.00000010 | $0.00000000 | 512 | nan | +| cohere.embed-multilingual-v3 | $0.00000010 | $0.00000000 | 512 | nan | +| meta.llama2-13b-chat-v1 | $0.00000075 | $0.00000100 | 4,096 | 4096 | +| meta.llama2-70b-chat-v1 | $0.00000195 | $0.00000256 | 4,096 | 4096 | +| meta.llama3-8b-instruct-v1:0 | $0.00000040 | $0.00000060 | 8,192 | 8192 | +| meta.llama3-70b-instruct-v1:0 | $0.00000265 | $0.00000350 | 8,192 | 8192 | +| 512-x-512/50-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan | +| 512-x-512/max-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan | +| max-x-max/50-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan | +| max-x-max/max-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan | +| 1024-x-1024/50-steps/stability.stable-diffusion-xl-v1 | -- | -- | 77 | nan | +| 1024-x-1024/max-steps/stability.stable-diffusion-xl-v1 | -- | -- | 77 | nan | +| sagemaker/meta-textgeneration-llama-2-7b | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| sagemaker/meta-textgeneration-llama-2-7b-f | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| sagemaker/meta-textgeneration-llama-2-13b | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| sagemaker/meta-textgeneration-llama-2-13b-f | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| sagemaker/meta-textgeneration-llama-2-70b | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| sagemaker/meta-textgeneration-llama-2-70b-b-f | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| together-ai-up-to-3b | $0.00000010 | $0.00000010 | nan | nan | +| together-ai-3.1b-7b | $0.00000020 | $0.00000020 | nan | nan | +| together-ai-7.1b-20b | $0.00000040 | $0.00000040 | nan | nan | +| together-ai-20.1b-40b | $0.00000080 | $0.00000080 | nan | nan | +| together-ai-40.1b-70b | $0.00000090 | $0.00000090 | nan | nan | +| together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1 | $0.00000060 | $0.00000060 | nan | nan | +| together_ai/mistralai/Mistral-7B-Instruct-v0.1 | -- | -- | nan | nan | +| together_ai/togethercomputer/CodeLlama-34b-Instruct | -- | -- | nan | nan | +| ollama/llama2 | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/llama2:13b | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/llama2:70b | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/llama2-uncensored | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/mistral | $0.00000000 | $0.00000000 | 8,192 | 8192 | +| ollama/codellama | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/orca-mini | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/vicuna | $0.00000000 | $0.00000000 | 2,048 | 2048 | +| deepinfra/lizpreciatior/lzlv_70b_fp16_hf | $0.00000070 | $0.00000090 | 4,096 | 4096 | +| deepinfra/Gryphe/MythoMax-L2-13b | $0.00000022 | $0.00000022 | 4,096 | 4096 | +| deepinfra/mistralai/Mistral-7B-Instruct-v0.1 | $0.00000013 | $0.00000013 | 32,768 | 8191 | +| deepinfra/meta-llama/Llama-2-70b-chat-hf | $0.00000070 | $0.00000090 | 4,096 | 4096 | +| deepinfra/cognitivecomputations/dolphin-2.6-mixtral-8x7b | $0.00000027 | $0.00000027 | 32,768 | 8191 | +| deepinfra/codellama/CodeLlama-34b-Instruct-hf | $0.00000060 | $0.00000060 | 4,096 | 4096 | +| deepinfra/deepinfra/mixtral | $0.00000027 | $0.00000027 | 32,000 | 4096 | +| deepinfra/Phind/Phind-CodeLlama-34B-v2 | $0.00000060 | $0.00000060 | 16,384 | 4096 | +| deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1 | $0.00000027 | $0.00000027 | 32,768 | 8191 | +| deepinfra/deepinfra/airoboros-70b | $0.00000070 | $0.00000090 | 4,096 | 4096 | +| deepinfra/01-ai/Yi-34B-Chat | $0.00000060 | $0.00000060 | 4,096 | 4096 | +| deepinfra/01-ai/Yi-6B-200K | $0.00000013 | $0.00000013 | 200,000 | 4096 | +| deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1 | $0.00000070 | $0.00000090 | 4,096 | 4096 | +| deepinfra/meta-llama/Llama-2-13b-chat-hf | $0.00000022 | $0.00000022 | 4,096 | 4096 | +| deepinfra/amazon/MistralLite | $0.00000020 | $0.00000020 | 32,768 | 8191 | +| deepinfra/meta-llama/Llama-2-7b-chat-hf | $0.00000013 | $0.00000013 | 4,096 | 4096 | +| deepinfra/01-ai/Yi-34B-200K | $0.00000060 | $0.00000060 | 200,000 | 4096 | +| deepinfra/openchat/openchat_3.5 | $0.00000013 | $0.00000013 | 4,096 | 4096 | +| perplexity/codellama-34b-instruct | $0.00000035 | $0.00000140 | 16,384 | 16384 | +| perplexity/codellama-70b-instruct | $0.00000070 | $0.00000280 | 16,384 | 16384 | +| perplexity/pplx-7b-chat | $0.00000007 | $0.00000028 | 8,192 | 8192 | +| perplexity/pplx-70b-chat | $0.00000070 | $0.00000280 | 4,096 | 4096 | +| perplexity/pplx-7b-online | $0.00000000 | $0.00000028 | 4,096 | 4096 | +| perplexity/pplx-70b-online | $0.00000000 | $0.00000280 | 4,096 | 4096 | +| perplexity/llama-2-70b-chat | $0.00000070 | $0.00000280 | 4,096 | 4096 | +| perplexity/mistral-7b-instruct | $0.00000007 | $0.00000028 | 4,096 | 4096 | +| perplexity/mixtral-8x7b-instruct | $0.00000007 | $0.00000028 | 4,096 | 4096 | +| perplexity/sonar-small-chat | $0.00000007 | $0.00000028 | 16,384 | 16384 | +| perplexity/sonar-small-online | $0.00000000 | $0.00000028 | 12,000 | 12000 | +| perplexity/sonar-medium-chat | $0.00000060 | $0.00000180 | 16,384 | 16384 | +| perplexity/sonar-medium-online | $0.00000000 | $0.00000180 | 12,000 | 12000 | +| anyscale/mistralai/Mistral-7B-Instruct-v0.1 | $0.00000015 | $0.00000015 | 16,384 | 16384 | +| anyscale/Mixtral-8x7B-Instruct-v0.1 | $0.00000015 | $0.00000015 | 16,384 | 16384 | +| anyscale/HuggingFaceH4/zephyr-7b-beta | $0.00000015 | $0.00000015 | 16,384 | 16384 | +| anyscale/meta-llama/Llama-2-7b-chat-hf | $0.00000015 | $0.00000015 | 4,096 | 4096 | +| anyscale/meta-llama/Llama-2-13b-chat-hf | $0.00000025 | $0.00000025 | 4,096 | 4096 | +| anyscale/meta-llama/Llama-2-70b-chat-hf | $0.00000100 | $0.00000100 | 4,096 | 4096 | +| anyscale/codellama/CodeLlama-34b-Instruct-hf | $0.00000100 | $0.00000100 | 4,096 | 4096 | +| cloudflare/@cf/meta/llama-2-7b-chat-fp16 | $0.00000192 | $0.00000192 | 3,072 | 3072 | +| cloudflare/@cf/meta/llama-2-7b-chat-int8 | $0.00000192 | $0.00000192 | 2,048 | 2048 | +| cloudflare/@cf/mistral/mistral-7b-instruct-v0.1 | $0.00000192 | $0.00000192 | 8,192 | 8192 | +| cloudflare/@hf/thebloke/codellama-7b-instruct-awq | $0.00000192 | $0.00000192 | 4,096 | 4096 | +| voyage/voyage-01 | $0.00000010 | $0.00000000 | 4,096 | nan | +| voyage/voyage-lite-01 | $0.00000010 | $0.00000000 | 4,096 | nan | +| voyage/voyage-large-2 | $0.00000012 | $0.00000000 | 16,000 | nan | +| voyage/voyage-law-2 | $0.00000012 | $0.00000000 | 16,000 | nan | +| voyage/voyage-code-2 | $0.00000012 | $0.00000000 | 16,000 | nan | +| voyage/voyage-2 | $0.00000010 | $0.00000000 | 4,000 | nan | +| voyage/voyage-lite-02-instruct | $0.00000010 | $0.00000000 | 4,000 | nan | ### Callback handlers You may also calculate token costs in LLM wrapper/framework libraries using callbacks. diff --git a/pricing_table.md b/pricing_table.md index 65c6084..5c448d8 100644 --- a/pricing_table.md +++ b/pricing_table.md @@ -1,378 +1,379 @@ -| | max_tokens | max_input_tokens | input_cost_per_token | output_cost_per_token | -|:--------------------------------------------------------------------------------------------|:-------------|:-------------------|:-----------------------|:------------------------| -| gpt-4 | 4,096 | 8,192 | $0.00003000 | $0.00006000 | -| gpt-4o | 4,096 | 128,000 | $0.00000500 | $0.00001500 | -| gpt-4o-2024-05-13 | 4,096 | 128,000 | $0.00000500 | $0.00001500 | -| gpt-4-turbo-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-0314 | 4,096 | 8,192 | $0.00003000 | $0.00006000 | -| gpt-4-0613 | 4,096 | 8,192 | $0.00003000 | $0.00006000 | -| gpt-4-32k | 4,096 | 32,768 | $0.00006000 | $0.00012000 | -| gpt-4-32k-0314 | 4,096 | 32,768 | $0.00006000 | $0.00012000 | -| gpt-4-32k-0613 | 4,096 | 32,768 | $0.00006000 | $0.00012000 | -| gpt-4-turbo | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-turbo-2024-04-09 | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-1106-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-0125-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-vision-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-4-1106-vision-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| gpt-3.5-turbo | 4,097 | 16,385 | $0.00000150 | $0.00000200 | -| gpt-3.5-turbo-0301 | 4,097 | 4,097 | $0.00000150 | $0.00000200 | -| gpt-3.5-turbo-0613 | 4,097 | 4,097 | $0.00000150 | $0.00000200 | -| gpt-3.5-turbo-1106 | 16,385 | 16,385 | $0.00000100 | $0.00000200 | -| gpt-3.5-turbo-0125 | 16,385 | 16,385 | $0.00000050 | $0.00000150 | -| gpt-3.5-turbo-16k | 16,385 | 16,385 | $0.00000300 | $0.00000400 | -| gpt-3.5-turbo-16k-0613 | 16,385 | 16,385 | $0.00000300 | $0.00000400 | -| ft:gpt-3.5-turbo | 4,097 | 4,097 | $0.00000300 | $0.00000600 | -| text-embedding-3-large | 8,191 | 8,191 | $0.00000013 | $0.00000000 | -| text-embedding-3-small | 8,191 | 8,191 | $0.00000002 | $0.00000000 | -| text-embedding-ada-002 | 8,191 | 8,191 | $0.00000010 | $0.00000000 | -| text-embedding-ada-002-v2 | 8,191 | 8,191 | $0.00000010 | $0.00000000 | -| text-moderation-stable | 32,768 | 32,768 | $0.00000000 | $0.00000000 | -| text-moderation-007 | 32,768 | 32,768 | $0.00000000 | $0.00000000 | -| text-moderation-latest | 32,768 | 32,768 | $0.00000000 | $0.00000000 | -| 256-x-256/dall-e-2 | nan | nan | -- | -- | -| 512-x-512/dall-e-2 | nan | nan | -- | -- | -| 1024-x-1024/dall-e-2 | nan | nan | -- | -- | -| hd/1024-x-1792/dall-e-3 | nan | nan | -- | -- | -| hd/1792-x-1024/dall-e-3 | nan | nan | -- | -- | -| hd/1024-x-1024/dall-e-3 | nan | nan | -- | -- | -| standard/1024-x-1792/dall-e-3 | nan | nan | -- | -- | -| standard/1792-x-1024/dall-e-3 | nan | nan | -- | -- | -| standard/1024-x-1024/dall-e-3 | nan | nan | -- | -- | -| whisper-1 | nan | nan | -- | -- | -| azure/whisper-1 | nan | nan | -- | -- | -| azure/gpt-4-turbo-2024-04-09 | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| azure/gpt-4-0125-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| azure/gpt-4-1106-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| azure/gpt-4-0613 | 4,096 | 8,192 | $0.00003000 | $0.00006000 | -| azure/gpt-4-32k-0613 | 4,096 | 32,768 | $0.00006000 | $0.00012000 | -| azure/gpt-4-32k | 4,096 | 32,768 | $0.00006000 | $0.00012000 | -| azure/gpt-4 | 4,096 | 8,192 | $0.00003000 | $0.00006000 | -| azure/gpt-4-turbo | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| azure/gpt-4-turbo-vision-preview | 4,096 | 128,000 | $0.00001000 | $0.00003000 | -| azure/gpt-35-turbo-16k-0613 | 4,096 | 16,385 | $0.00000300 | $0.00000400 | -| azure/gpt-35-turbo-1106 | 4,096 | 16,384 | $0.00000150 | $0.00000200 | -| azure/gpt-35-turbo-0125 | 4,096 | 16,384 | $0.00000050 | $0.00000150 | -| azure/gpt-35-turbo-16k | 4,096 | 16,385 | $0.00000300 | $0.00000400 | -| azure/gpt-35-turbo | 4,096 | 4,097 | $0.00000150 | $0.00000200 | -| azure/gpt-3.5-turbo-instruct-0914 | 4,097 | 4,097 | $0.00000150 | $0.00000200 | -| azure/gpt-35-turbo-instruct | 4,097 | 4,097 | $0.00000150 | $0.00000200 | -| azure/mistral-large-latest | 32,000 | 32,000 | $0.00000800 | $0.00002400 | -| azure/mistral-large-2402 | 32,000 | 32,000 | $0.00000800 | $0.00002400 | -| azure/command-r-plus | 4,096 | 128,000 | $0.00000300 | $0.00001500 | -| azure/ada | 8,191 | 8,191 | $0.00000010 | $0.00000000 | -| azure/text-embedding-ada-002 | 8,191 | 8,191 | $0.00000010 | $0.00000000 | -| azure/text-embedding-3-large | 8,191 | 8,191 | $0.00000013 | $0.00000000 | -| azure/text-embedding-3-small | 8,191 | 8,191 | $0.00000002 | $0.00000000 | -| azure/standard/1024-x-1024/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/hd/1024-x-1024/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/standard/1024-x-1792/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/standard/1792-x-1024/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/hd/1024-x-1792/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/hd/1792-x-1024/dall-e-3 | nan | nan | -- | $0.00000000 | -| azure/standard/1024-x-1024/dall-e-2 | nan | nan | -- | $0.00000000 | -| babbage-002 | 16,384 | 16,384 | $0.00000040 | $0.00000040 | -| davinci-002 | 16,384 | 16,384 | $0.00000200 | $0.00000200 | -| gpt-3.5-turbo-instruct | 4,096 | 8,192 | $0.00000150 | $0.00000200 | -| gpt-3.5-turbo-instruct-0914 | 4,097 | 8,192 | $0.00000150 | $0.00000200 | -| claude-instant-1 | 8,191 | 100,000 | $0.00000163 | $0.00000551 | -| mistral/mistral-tiny | 8,191 | 32,000 | $0.00000015 | $0.00000046 | -| mistral/mistral-small | 8,191 | 32,000 | $0.00000200 | $0.00000600 | -| mistral/mistral-small-latest | 8,191 | 32,000 | $0.00000200 | $0.00000600 | -| mistral/mistral-medium | 8,191 | 32,000 | $0.00000270 | $0.00000810 | -| mistral/mistral-medium-latest | 8,191 | 32,000 | $0.00000270 | $0.00000810 | -| mistral/mistral-medium-2312 | 8,191 | 32,000 | $0.00000270 | $0.00000810 | -| mistral/mistral-large-latest | 8,191 | 32,000 | $0.00000800 | $0.00002400 | -| mistral/mistral-large-2402 | 8,191 | 32,000 | $0.00000800 | $0.00002400 | -| mistral/open-mixtral-8x7b | 8,191 | 32,000 | $0.00000200 | $0.00000600 | -| mistral/mistral-embed | 8,192 | 8,192 | $0.00000011 | -- | -| deepseek-chat | 4,096 | 32,000 | $0.00000014 | $0.00000028 | -| deepseek-coder | 4,096 | 16,000 | $0.00000014 | $0.00000028 | -| groq/llama2-70b-4096 | 4,096 | 4,096 | $0.00000070 | $0.00000080 | -| groq/llama3-8b-8192 | 8,192 | 8,192 | $0.00000010 | $0.00000010 | -| groq/llama3-70b-8192 | 8,192 | 8,192 | $0.00000064 | $0.00000080 | -| groq/mixtral-8x7b-32768 | 32,768 | 32,768 | $0.00000027 | $0.00000027 | -| groq/gemma-7b-it | 8,192 | 8,192 | $0.00000010 | $0.00000010 | -| claude-instant-1.2 | 8,191 | 100,000 | $0.00000016 | $0.00000055 | -| claude-2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| claude-2.1 | 8,191 | 200,000 | $0.00000800 | $0.00002400 | -| claude-3-haiku-20240307 | 4,096 | 200,000 | $0.00000025 | $0.00000125 | -| claude-3-opus-20240229 | 4,096 | 200,000 | $0.00001500 | $0.00007500 | -| claude-3-sonnet-20240229 | 4,096 | 200,000 | $0.00000300 | $0.00001500 | -| text-bison | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| text-bison@001 | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| text-unicorn | 1,024 | 8,192 | $0.00001000 | $0.00002800 | -| text-unicorn@001 | 1,024 | 8,192 | $0.00001000 | $0.00002800 | -| chat-bison | 4,096 | 8,192 | $0.00000012 | $0.00000012 | -| chat-bison@001 | 4,096 | 8,192 | $0.00000012 | $0.00000012 | -| chat-bison@002 | 4,096 | 8,192 | $0.00000012 | $0.00000012 | -| chat-bison-32k | 8,192 | 32,000 | $0.00000012 | $0.00000012 | -| code-bison | 1,024 | 6,144 | $0.00000012 | $0.00000012 | -| code-bison@001 | 1,024 | 6,144 | $0.00000012 | $0.00000012 | -| code-gecko@001 | 64 | 2,048 | $0.00000012 | $0.00000012 | -| code-gecko@002 | 64 | 2,048 | $0.00000012 | $0.00000012 | -| code-gecko | 64 | 2,048 | $0.00000012 | $0.00000012 | -| codechat-bison | 1,024 | 6,144 | $0.00000012 | $0.00000012 | -| codechat-bison@001 | 1,024 | 6,144 | $0.00000012 | $0.00000012 | -| codechat-bison-32k | 8,192 | 32,000 | $0.00000012 | $0.00000012 | -| gemini-pro | 8,192 | 32,760 | $0.00000025 | $0.00000050 | -| gemini-1.0-pro | 8,192 | 32,760 | $0.00000025 | $0.00000050 | -| gemini-1.0-pro-001 | 8,192 | 32,760 | $0.00000025 | $0.00000050 | -| gemini-1.0-pro-002 | 8,192 | 32,760 | $0.00000025 | $0.00000050 | -| gemini-1.5-pro | 8,192 | 1,000,000 | $0.00000063 | $0.00000188 | -| gemini-1.5-pro-preview-0215 | 8,192 | 1,000,000 | $0.00000063 | $0.00000188 | -| gemini-1.5-pro-preview-0409 | 8,192 | 1,000,000 | $0.00000063 | $0.00000188 | -| gemini-experimental | 8,192 | 1,000,000 | $0.00000000 | $0.00000000 | -| gemini-pro-vision | 2,048 | 16,384 | $0.00000025 | $0.00000050 | -| gemini-1.0-pro-vision | 2,048 | 16,384 | $0.00000025 | $0.00000050 | -| gemini-1.0-pro-vision-001 | 2,048 | 16,384 | $0.00000025 | $0.00000050 | -| vertex_ai/claude-3-sonnet@20240229 | 4,096 | 200,000 | $0.00000300 | $0.00001500 | -| vertex_ai/claude-3-haiku@20240307 | 4,096 | 200,000 | $0.00000025 | $0.00000125 | -| vertex_ai/claude-3-opus@20240229 | 4,096 | 200,000 | $0.00000150 | $0.00000750 | -| textembedding-gecko | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| textembedding-gecko-multilingual | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| textembedding-gecko-multilingual@001 | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| textembedding-gecko@001 | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| textembedding-gecko@003 | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| text-embedding-preview-0409 | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| text-multilingual-embedding-preview-0409 | 3,072 | 3,072 | $0.00000001 | $0.00000000 | -| palm/chat-bison | 4,096 | 8,192 | $0.00000012 | $0.00000012 | -| palm/chat-bison-001 | 4,096 | 8,192 | $0.00000012 | $0.00000012 | -| palm/text-bison | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| palm/text-bison-001 | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| palm/text-bison-safety-off | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| palm/text-bison-safety-recitation-off | 1,024 | 8,192 | $0.00000012 | $0.00000012 | -| gemini/gemini-pro | 8,192 | 32,760 | $0.00000000 | $0.00000000 | -| gemini/gemini-1.5-pro | 8,192 | 1,000,000 | $0.00000000 | $0.00000000 | -| gemini/gemini-1.5-pro-latest | 8,192 | 1,048,576 | $0.00000000 | $0.00000000 | -| gemini/gemini-pro-vision | 2,048 | 30,720 | $0.00000000 | $0.00000000 | -| command-r | 4,096 | 128,000 | $0.00000050 | $0.00000150 | -| command-light | 4,096 | 4,096 | $0.00001500 | $0.00001500 | -| command-r-plus | 4,096 | 128,000 | $0.00000300 | $0.00001500 | -| command-nightly | 4,096 | 4,096 | $0.00001500 | $0.00001500 | -| command | 4,096 | 4,096 | $0.00001500 | $0.00001500 | -| command-medium-beta | 4,096 | 4,096 | $0.00001500 | $0.00001500 | -| command-xlarge-beta | 4,096 | 4,096 | $0.00001500 | $0.00001500 | -| replicate/meta/llama-2-13b | 4,096 | 4,096 | $0.00000010 | $0.00000050 | -| replicate/meta/llama-2-13b-chat | 4,096 | 4,096 | $0.00000010 | $0.00000050 | -| replicate/meta/llama-2-70b | 4,096 | 4,096 | $0.00000065 | $0.00000275 | -| replicate/meta/llama-2-70b-chat | 4,096 | 4,096 | $0.00000065 | $0.00000275 | -| replicate/meta/llama-2-7b | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/meta/llama-2-7b-chat | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/meta/llama-3-70b | 4,096 | 4,096 | $0.00000065 | $0.00000275 | -| replicate/meta/llama-3-70b-instruct | 4,096 | 4,096 | $0.00000065 | $0.00000275 | -| replicate/meta/llama-3-8b | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/meta/llama-3-8b-instruct | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/mistralai/mistral-7b-v0.1 | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/mistralai/mistral-7b-instruct-v0.2 | 4,096 | 4,096 | $0.00000005 | $0.00000025 | -| replicate/mistralai/mixtral-8x7b-instruct-v0.1 | 4,096 | 4,096 | $0.00000030 | $0.00000100 | -| openrouter/microsoft/wizardlm-2-8x22b:nitro | 65,536 | nan | $0.00000100 | $0.00000100 | -| openrouter/google/gemini-pro-1.5 | 8,192 | 1,000,000 | $0.00000250 | $0.00000750 | -| openrouter/mistralai/mixtral-8x22b-instruct | 65,536 | nan | $0.00000065 | $0.00000065 | -| openrouter/cohere/command-r-plus | 128,000 | nan | $0.00000300 | $0.00001500 | -| openrouter/databricks/dbrx-instruct | 32,768 | nan | $0.00000060 | $0.00000060 | -| openrouter/anthropic/claude-3-haiku | 200,000 | nan | $0.00000025 | $0.00000125 | -| openrouter/anthropic/claude-3-sonnet | 200,000 | nan | $0.00000300 | $0.00001500 | -| openrouter/mistralai/mistral-large | 32,000 | nan | $0.00000800 | $0.00002400 | -| openrouter/cognitivecomputations/dolphin-mixtral-8x7b | 32,769 | nan | $0.00000050 | $0.00000050 | -| openrouter/google/gemini-pro-vision | 45,875 | nan | $0.00000012 | $0.00000038 | -| openrouter/fireworks/firellava-13b | 4,096 | nan | $0.00000020 | $0.00000020 | -| openrouter/meta-llama/llama-3-8b-instruct:free | 8,192 | nan | $0.00000000 | $0.00000000 | -| openrouter/meta-llama/llama-3-8b-instruct:extended | 16,384 | nan | $0.00000022 | $0.00000225 | -| openrouter/meta-llama/llama-3-70b-instruct:nitro | 8,192 | nan | $0.00000090 | $0.00000090 | -| openrouter/meta-llama/llama-3-70b-instruct | 8,192 | nan | $0.00000059 | $0.00000079 | -| openrouter/openai/gpt-4-vision-preview | 130,000 | nan | $0.00001000 | $0.00003000 | -| openrouter/openai/gpt-3.5-turbo | 4,095 | nan | $0.00000150 | $0.00000200 | -| openrouter/openai/gpt-3.5-turbo-16k | 16,383 | nan | $0.00000300 | $0.00000400 | -| openrouter/openai/gpt-4 | 8,192 | nan | $0.00003000 | $0.00006000 | -| openrouter/anthropic/claude-instant-v1 | 100,000 | nan | $0.00000163 | $0.00000551 | -| openrouter/anthropic/claude-2 | 100,000 | nan | $0.00001102 | $0.00003268 | -| openrouter/anthropic/claude-3-opus | 4,096 | 200,000 | $0.00001500 | $0.00007500 | -| openrouter/google/palm-2-chat-bison | 25,804 | nan | $0.00000050 | $0.00000050 | -| openrouter/google/palm-2-codechat-bison | 20,070 | nan | $0.00000050 | $0.00000050 | -| openrouter/meta-llama/llama-2-13b-chat | 4,096 | nan | $0.00000020 | $0.00000020 | -| openrouter/meta-llama/llama-2-70b-chat | 4,096 | nan | $0.00000150 | $0.00000150 | -| openrouter/meta-llama/codellama-34b-instruct | 8,096 | nan | $0.00000050 | $0.00000050 | -| openrouter/nousresearch/nous-hermes-llama2-13b | 4,096 | nan | $0.00000020 | $0.00000020 | -| openrouter/mancer/weaver | 8,000 | nan | $0.00000563 | $0.00000563 | -| openrouter/gryphe/mythomax-l2-13b | 8,192 | nan | $0.00000188 | $0.00000188 | -| openrouter/jondurbin/airoboros-l2-70b-2.1 | 4,096 | nan | $0.00001388 | $0.00001388 | -| openrouter/undi95/remm-slerp-l2-13b | 6,144 | nan | $0.00000188 | $0.00000188 | -| openrouter/pygmalionai/mythalion-13b | 4,096 | nan | $0.00000188 | $0.00000188 | -| openrouter/mistralai/mistral-7b-instruct | 8,192 | nan | $0.00000013 | $0.00000013 | -| openrouter/mistralai/mistral-7b-instruct:free | 8,192 | nan | $0.00000000 | $0.00000000 | -| j2-ultra | 8,192 | 8,192 | $0.00001500 | $0.00001500 | -| j2-mid | 8,192 | 8,192 | $0.00001000 | $0.00001000 | -| j2-light | 8,192 | 8,192 | $0.00000300 | $0.00000300 | -| dolphin | 16,384 | 16,384 | $0.00000050 | $0.00000050 | -| chatdolphin | 16,384 | 16,384 | $0.00000050 | $0.00000050 | -| luminous-base | 2,048 | nan | $0.00003000 | $0.00003300 | -| luminous-base-control | 2,048 | nan | $0.00003750 | $0.00004125 | -| luminous-extended | 2,048 | nan | $0.00004500 | $0.00004950 | -| luminous-extended-control | 2,048 | nan | $0.00005625 | $0.00006187 | -| luminous-supreme | 2,048 | nan | $0.00017500 | $0.00019250 | -| luminous-supreme-control | 2,048 | nan | $0.00021875 | $0.00024063 | -| ai21.j2-mid-v1 | 8,191 | 8,191 | $0.00001250 | $0.00001250 | -| ai21.j2-ultra-v1 | 8,191 | 8,191 | $0.00001880 | $0.00001880 | -| amazon.titan-text-lite-v1 | 4,000 | 42,000 | $0.00000030 | $0.00000040 | -| amazon.titan-text-express-v1 | 8,000 | 42,000 | $0.00000130 | $0.00000170 | -| amazon.titan-embed-text-v1 | 8,192 | 8,192 | $0.00000010 | $0.00000000 | -| amazon.titan-embed-text-v2:0 | 8,192 | 8,192 | $0.00000020 | $0.00000000 | -| mistral.mistral-7b-instruct-v0:2 | 8,191 | 32,000 | $0.00000015 | $0.00000020 | -| mistral.mixtral-8x7b-instruct-v0:1 | 8,191 | 32,000 | $0.00000045 | $0.00000070 | -| mistral.mistral-large-2402-v1:0 | 8,191 | 32,000 | $0.00000800 | $0.00002400 | -| bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1 | 8,191 | 32,000 | $0.00000045 | $0.00000070 | -| bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1 | 8,191 | 32,000 | $0.00000045 | $0.00000070 | -| bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1 | 8,191 | 32,000 | $0.00000059 | $0.00000091 | -| bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2 | 8,191 | 32,000 | $0.00000015 | $0.00000020 | -| bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2 | 8,191 | 32,000 | $0.00000015 | $0.00000020 | -| bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2 | 8,191 | 32,000 | $0.00000020 | $0.00000026 | -| bedrock/us-east-1/mistral.mistral-large-2402-v1:0 | 8,191 | 32,000 | $0.00000800 | $0.00002400 | -| bedrock/us-west-2/mistral.mistral-large-2402-v1:0 | 8,191 | 32,000 | $0.00000800 | $0.00002400 | -| bedrock/eu-west-3/mistral.mistral-large-2402-v1:0 | 8,191 | 32,000 | $0.00001040 | $0.00003120 | -| anthropic.claude-3-sonnet-20240229-v1:0 | 4,096 | 200,000 | $0.00000300 | $0.00001500 | -| anthropic.claude-3-haiku-20240307-v1:0 | 4,096 | 200,000 | $0.00000025 | $0.00000125 | -| anthropic.claude-3-opus-20240229-v1:0 | 4,096 | 200,000 | $0.00001500 | $0.00007500 | -| anthropic.claude-v1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-east-1/anthropic.claude-v1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-west-2/anthropic.claude-v1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/anthropic.claude-v1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/anthropic.claude-v1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/1-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/6-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/1-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/6-month-commitment/anthropic.claude-v1 | 8,191 | 100,000 | -- | -- | -| anthropic.claude-v2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-east-1/anthropic.claude-v2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-west-2/anthropic.claude-v2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/anthropic.claude-v2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/anthropic.claude-v2 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/1-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/6-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/1-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/6-month-commitment/anthropic.claude-v2 | 8,191 | 100,000 | -- | -- | -| anthropic.claude-v2:1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-east-1/anthropic.claude-v2:1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/us-west-2/anthropic.claude-v2:1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/anthropic.claude-v2:1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/anthropic.claude-v2:1 | 8,191 | 100,000 | $0.00000800 | $0.00002400 | -| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1 | 8,191 | 100,000 | -- | -- | -| anthropic.claude-instant-v1 | 8,191 | 100,000 | $0.00000163 | $0.00000551 | -| bedrock/us-east-1/anthropic.claude-instant-v1 | 8,191 | 100,000 | $0.00000080 | $0.00000240 | -| bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/us-west-2/anthropic.claude-instant-v1 | 8,191 | 100,000 | $0.00000080 | $0.00000240 | -| bedrock/ap-northeast-1/anthropic.claude-instant-v1 | 8,191 | 100,000 | $0.00000223 | $0.00000755 | -| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/anthropic.claude-instant-v1 | 8,191 | 100,000 | $0.00000248 | $0.00000838 | -| bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1 | 8,191 | 100,000 | -- | -- | -| cohere.command-text-v14 | 4,096 | 4,096 | $0.00000150 | $0.00000200 | -| bedrock/*/1-month-commitment/cohere.command-text-v14 | 4,096 | 4,096 | -- | -- | -| bedrock/*/6-month-commitment/cohere.command-text-v14 | 4,096 | 4,096 | -- | -- | -| cohere.command-light-text-v14 | 4,096 | 4,096 | $0.00000030 | $0.00000060 | -| bedrock/*/1-month-commitment/cohere.command-light-text-v14 | 4,096 | 4,096 | -- | -- | -| bedrock/*/6-month-commitment/cohere.command-light-text-v14 | 4,096 | 4,096 | -- | -- | -| cohere.command-r-plus-v1:0 | 4,096 | 128,000 | $0.00000300 | $0.00001500 | -| cohere.command-r-v1:0 | 4,096 | 128,000 | $0.00000050 | $0.00000150 | -| cohere.embed-english-v3 | 512 | 512 | $0.00000010 | $0.00000000 | -| cohere.embed-multilingual-v3 | 512 | 512 | $0.00000010 | $0.00000000 | -| meta.llama2-13b-chat-v1 | 4,096 | 4,096 | $0.00000075 | $0.00000100 | -| meta.llama2-70b-chat-v1 | 4,096 | 4,096 | $0.00000195 | $0.00000256 | -| meta.llama3-8b-instruct-v1:0 | 8,192 | 8,192 | $0.00000040 | $0.00000060 | -| meta.llama3-70b-instruct-v1:0 | 8,192 | 8,192 | $0.00000265 | $0.00000350 | -| 512-x-512/50-steps/stability.stable-diffusion-xl-v0 | 77 | 77 | -- | -- | -| 512-x-512/max-steps/stability.stable-diffusion-xl-v0 | 77 | 77 | -- | -- | -| max-x-max/50-steps/stability.stable-diffusion-xl-v0 | 77 | 77 | -- | -- | -| max-x-max/max-steps/stability.stable-diffusion-xl-v0 | 77 | 77 | -- | -- | -| 1024-x-1024/50-steps/stability.stable-diffusion-xl-v1 | 77 | 77 | -- | -- | -| 1024-x-1024/max-steps/stability.stable-diffusion-xl-v1 | 77 | 77 | -- | -- | -| sagemaker/meta-textgeneration-llama-2-7b | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| sagemaker/meta-textgeneration-llama-2-7b-f | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| sagemaker/meta-textgeneration-llama-2-13b | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| sagemaker/meta-textgeneration-llama-2-13b-f | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| sagemaker/meta-textgeneration-llama-2-70b | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| sagemaker/meta-textgeneration-llama-2-70b-b-f | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| together-ai-up-to-3b | nan | nan | $0.00000010 | $0.00000010 | -| together-ai-3.1b-7b | nan | nan | $0.00000020 | $0.00000020 | -| together-ai-7.1b-20b | 1,000 | nan | $0.00000040 | $0.00000040 | -| together-ai-20.1b-40b | nan | nan | $0.00000080 | $0.00000080 | -| together-ai-40.1b-70b | nan | nan | $0.00000090 | $0.00000090 | -| together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1 | nan | nan | $0.00000060 | $0.00000060 | -| together_ai/mistralai/Mistral-7B-Instruct-v0.1 | nan | nan | -- | -- | -| together_ai/togethercomputer/CodeLlama-34b-Instruct | nan | nan | -- | -- | -| ollama/llama2 | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/llama2:13b | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/llama2:70b | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/llama2-uncensored | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/mistral | 8,192 | 8,192 | $0.00000000 | $0.00000000 | -| ollama/codellama | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/orca-mini | 4,096 | 4,096 | $0.00000000 | $0.00000000 | -| ollama/vicuna | 2,048 | 2,048 | $0.00000000 | $0.00000000 | -| deepinfra/lizpreciatior/lzlv_70b_fp16_hf | 4,096 | 4,096 | $0.00000070 | $0.00000090 | -| deepinfra/Gryphe/MythoMax-L2-13b | 4,096 | 4,096 | $0.00000022 | $0.00000022 | -| deepinfra/mistralai/Mistral-7B-Instruct-v0.1 | 8,191 | 32,768 | $0.00000013 | $0.00000013 | -| deepinfra/meta-llama/Llama-2-70b-chat-hf | 4,096 | 4,096 | $0.00000070 | $0.00000090 | -| deepinfra/cognitivecomputations/dolphin-2.6-mixtral-8x7b | 8,191 | 32,768 | $0.00000027 | $0.00000027 | -| deepinfra/codellama/CodeLlama-34b-Instruct-hf | 4,096 | 4,096 | $0.00000060 | $0.00000060 | -| deepinfra/deepinfra/mixtral | 4,096 | 32,000 | $0.00000027 | $0.00000027 | -| deepinfra/Phind/Phind-CodeLlama-34B-v2 | 4,096 | 16,384 | $0.00000060 | $0.00000060 | -| deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1 | 8,191 | 32,768 | $0.00000027 | $0.00000027 | -| deepinfra/deepinfra/airoboros-70b | 4,096 | 4,096 | $0.00000070 | $0.00000090 | -| deepinfra/01-ai/Yi-34B-Chat | 4,096 | 4,096 | $0.00000060 | $0.00000060 | -| deepinfra/01-ai/Yi-6B-200K | 4,096 | 200,000 | $0.00000013 | $0.00000013 | -| deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1 | 4,096 | 4,096 | $0.00000070 | $0.00000090 | -| deepinfra/meta-llama/Llama-2-13b-chat-hf | 4,096 | 4,096 | $0.00000022 | $0.00000022 | -| deepinfra/amazon/MistralLite | 8,191 | 32,768 | $0.00000020 | $0.00000020 | -| deepinfra/meta-llama/Llama-2-7b-chat-hf | 4,096 | 4,096 | $0.00000013 | $0.00000013 | -| deepinfra/01-ai/Yi-34B-200K | 4,096 | 200,000 | $0.00000060 | $0.00000060 | -| deepinfra/openchat/openchat_3.5 | 4,096 | 4,096 | $0.00000013 | $0.00000013 | -| perplexity/codellama-34b-instruct | 16,384 | 16,384 | $0.00000035 | $0.00000140 | -| perplexity/codellama-70b-instruct | 16,384 | 16,384 | $0.00000070 | $0.00000280 | -| perplexity/pplx-7b-chat | 8,192 | 8,192 | $0.00000007 | $0.00000028 | -| perplexity/pplx-70b-chat | 4,096 | 4,096 | $0.00000070 | $0.00000280 | -| perplexity/pplx-7b-online | 4,096 | 4,096 | $0.00000000 | $0.00000028 | -| perplexity/pplx-70b-online | 4,096 | 4,096 | $0.00000000 | $0.00000280 | -| perplexity/llama-2-70b-chat | 4,096 | 4,096 | $0.00000070 | $0.00000280 | -| perplexity/mistral-7b-instruct | 4,096 | 4,096 | $0.00000007 | $0.00000028 | -| perplexity/mixtral-8x7b-instruct | 4,096 | 4,096 | $0.00000007 | $0.00000028 | -| perplexity/sonar-small-chat | 16,384 | 16,384 | $0.00000007 | $0.00000028 | -| perplexity/sonar-small-online | 12,000 | 12,000 | $0.00000000 | $0.00000028 | -| perplexity/sonar-medium-chat | 16,384 | 16,384 | $0.00000060 | $0.00000180 | -| perplexity/sonar-medium-online | 12,000 | 12,000 | $0.00000000 | $0.00000180 | -| anyscale/mistralai/Mistral-7B-Instruct-v0.1 | 16,384 | 16,384 | $0.00000015 | $0.00000015 | -| anyscale/Mixtral-8x7B-Instruct-v0.1 | 16,384 | 16,384 | $0.00000015 | $0.00000015 | -| anyscale/HuggingFaceH4/zephyr-7b-beta | 16,384 | 16,384 | $0.00000015 | $0.00000015 | -| anyscale/meta-llama/Llama-2-7b-chat-hf | 4,096 | 4,096 | $0.00000015 | $0.00000015 | -| anyscale/meta-llama/Llama-2-13b-chat-hf | 4,096 | 4,096 | $0.00000025 | $0.00000025 | -| anyscale/meta-llama/Llama-2-70b-chat-hf | 4,096 | 4,096 | $0.00000100 | $0.00000100 | -| anyscale/codellama/CodeLlama-34b-Instruct-hf | 4,096 | 4,096 | $0.00000100 | $0.00000100 | -| cloudflare/@cf/meta/llama-2-7b-chat-fp16 | 3,072 | 3,072 | $0.00000192 | $0.00000192 | -| cloudflare/@cf/meta/llama-2-7b-chat-int8 | 2,048 | 2,048 | $0.00000192 | $0.00000192 | -| cloudflare/@cf/mistral/mistral-7b-instruct-v0.1 | 8,192 | 8,192 | $0.00000192 | $0.00000192 | -| cloudflare/@hf/thebloke/codellama-7b-instruct-awq | 4,096 | 4,096 | $0.00000192 | $0.00000192 | -| voyage/voyage-01 | 4,096 | 4,096 | $0.00000010 | $0.00000000 | -| voyage/voyage-lite-01 | 4,096 | 4,096 | $0.00000010 | $0.00000000 | -| voyage/voyage-large-2 | 16,000 | 16,000 | $0.00000012 | $0.00000000 | -| voyage/voyage-law-2 | 16,000 | 16,000 | $0.00000012 | $0.00000000 | -| voyage/voyage-code-2 | 16,000 | 16,000 | $0.00000012 | $0.00000000 | -| voyage/voyage-2 | 4,000 | 4,000 | $0.00000010 | $0.00000000 | -| voyage/voyage-lite-02-instruct | 4,000 | 4,000 | $0.00000010 | $0.00000000 | \ No newline at end of file +| Model Name | Prompt Cost (USD) | Completion Cost (USD) | Max Prompt Tokens | Max Output Tokens | +|:--------------------------------------------------------------------------------------------|:--------------------|:------------------------|:--------------------|--------------------:| +| gpt-4 | $0.00003000 | $0.00006000 | 8,192 | 4096 | +| gpt-4o | $0.00000500 | $0.00001500 | 128,000 | 4096 | +| gpt-4o-2024-05-13 | $0.00000500 | $0.00001500 | 128,000 | 4096 | +| gpt-4-turbo-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-0314 | $0.00003000 | $0.00006000 | 8,192 | 4096 | +| gpt-4-0613 | $0.00003000 | $0.00006000 | 8,192 | 4096 | +| gpt-4-32k | $0.00006000 | $0.00012000 | 32,768 | 4096 | +| gpt-4-32k-0314 | $0.00006000 | $0.00012000 | 32,768 | 4096 | +| gpt-4-32k-0613 | $0.00006000 | $0.00012000 | 32,768 | 4096 | +| gpt-4-turbo | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-turbo-2024-04-09 | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-1106-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-0125-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-vision-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-4-1106-vision-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| gpt-3.5-turbo | $0.00000150 | $0.00000200 | 16,385 | 4096 | +| gpt-3.5-turbo-0301 | $0.00000150 | $0.00000200 | 4,097 | 4096 | +| gpt-3.5-turbo-0613 | $0.00000150 | $0.00000200 | 4,097 | 4096 | +| gpt-3.5-turbo-1106 | $0.00000100 | $0.00000200 | 16,385 | 4096 | +| gpt-3.5-turbo-0125 | $0.00000050 | $0.00000150 | 16,385 | 4096 | +| gpt-3.5-turbo-16k | $0.00000300 | $0.00000400 | 16,385 | 4096 | +| gpt-3.5-turbo-16k-0613 | $0.00000300 | $0.00000400 | 16,385 | 4096 | +| ft:gpt-3.5-turbo | $0.00000300 | $0.00000600 | 4,097 | 4096 | +| text-embedding-3-large | $0.00000013 | $0.00000000 | 8,191 | nan | +| text-embedding-3-small | $0.00000002 | $0.00000000 | 8,191 | nan | +| text-embedding-ada-002 | $0.00000010 | $0.00000000 | 8,191 | nan | +| text-embedding-ada-002-v2 | $0.00000010 | $0.00000000 | 8,191 | nan | +| text-moderation-stable | $0.00000000 | $0.00000000 | 32,768 | 0 | +| text-moderation-007 | $0.00000000 | $0.00000000 | 32,768 | 0 | +| text-moderation-latest | $0.00000000 | $0.00000000 | 32,768 | 0 | +| 256-x-256/dall-e-2 | -- | -- | nan | nan | +| 512-x-512/dall-e-2 | -- | -- | nan | nan | +| 1024-x-1024/dall-e-2 | -- | -- | nan | nan | +| hd/1024-x-1792/dall-e-3 | -- | -- | nan | nan | +| hd/1792-x-1024/dall-e-3 | -- | -- | nan | nan | +| hd/1024-x-1024/dall-e-3 | -- | -- | nan | nan | +| standard/1024-x-1792/dall-e-3 | -- | -- | nan | nan | +| standard/1792-x-1024/dall-e-3 | -- | -- | nan | nan | +| standard/1024-x-1024/dall-e-3 | -- | -- | nan | nan | +| whisper-1 | -- | -- | nan | nan | +| azure/whisper-1 | -- | -- | nan | nan | +| azure/gpt-4-turbo-2024-04-09 | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| azure/gpt-4-0125-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| azure/gpt-4-1106-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| azure/gpt-4-0613 | $0.00003000 | $0.00006000 | 8,192 | 4096 | +| azure/gpt-4-32k-0613 | $0.00006000 | $0.00012000 | 32,768 | 4096 | +| azure/gpt-4-32k | $0.00006000 | $0.00012000 | 32,768 | 4096 | +| azure/gpt-4 | $0.00003000 | $0.00006000 | 8,192 | 4096 | +| azure/gpt-4-turbo | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| azure/gpt-4-turbo-vision-preview | $0.00001000 | $0.00003000 | 128,000 | 4096 | +| azure/gpt-35-turbo-16k-0613 | $0.00000300 | $0.00000400 | 16,385 | 4096 | +| azure/gpt-35-turbo-1106 | $0.00000150 | $0.00000200 | 16,384 | 4096 | +| azure/gpt-35-turbo-0125 | $0.00000050 | $0.00000150 | 16,384 | 4096 | +| azure/gpt-35-turbo-16k | $0.00000300 | $0.00000400 | 16,385 | 4096 | +| azure/gpt-35-turbo | $0.00000150 | $0.00000200 | 4,097 | 4096 | +| azure/gpt-3.5-turbo-instruct-0914 | $0.00000150 | $0.00000200 | 4,097 | nan | +| azure/gpt-35-turbo-instruct | $0.00000150 | $0.00000200 | 4,097 | nan | +| azure/mistral-large-latest | $0.00000800 | $0.00002400 | 32,000 | nan | +| azure/mistral-large-2402 | $0.00000800 | $0.00002400 | 32,000 | nan | +| azure/command-r-plus | $0.00000300 | $0.00001500 | 128,000 | 4096 | +| azure/ada | $0.00000010 | $0.00000000 | 8,191 | nan | +| azure/text-embedding-ada-002 | $0.00000010 | $0.00000000 | 8,191 | nan | +| azure/text-embedding-3-large | $0.00000013 | $0.00000000 | 8,191 | nan | +| azure/text-embedding-3-small | $0.00000002 | $0.00000000 | 8,191 | nan | +| azure/standard/1024-x-1024/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/hd/1024-x-1024/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/standard/1024-x-1792/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/standard/1792-x-1024/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/hd/1024-x-1792/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/hd/1792-x-1024/dall-e-3 | -- | $0.00000000 | nan | nan | +| azure/standard/1024-x-1024/dall-e-2 | -- | $0.00000000 | nan | nan | +| babbage-002 | $0.00000040 | $0.00000040 | 16,384 | 4096 | +| davinci-002 | $0.00000200 | $0.00000200 | 16,384 | 4096 | +| gpt-3.5-turbo-instruct | $0.00000150 | $0.00000200 | 8,192 | 4096 | +| gpt-3.5-turbo-instruct-0914 | $0.00000150 | $0.00000200 | 8,192 | 4097 | +| claude-instant-1 | $0.00000163 | $0.00000551 | 100,000 | 8191 | +| mistral/mistral-tiny | $0.00000015 | $0.00000046 | 32,000 | 8191 | +| mistral/mistral-small | $0.00000200 | $0.00000600 | 32,000 | 8191 | +| mistral/mistral-small-latest | $0.00000200 | $0.00000600 | 32,000 | 8191 | +| mistral/mistral-medium | $0.00000270 | $0.00000810 | 32,000 | 8191 | +| mistral/mistral-medium-latest | $0.00000270 | $0.00000810 | 32,000 | 8191 | +| mistral/mistral-medium-2312 | $0.00000270 | $0.00000810 | 32,000 | 8191 | +| mistral/mistral-large-latest | $0.00000800 | $0.00002400 | 32,000 | 8191 | +| mistral/mistral-large-2402 | $0.00000800 | $0.00002400 | 32,000 | 8191 | +| mistral/open-mixtral-8x7b | $0.00000200 | $0.00000600 | 32,000 | 8191 | +| mistral/mistral-embed | $0.00000011 | -- | 8,192 | nan | +| deepseek-chat | $0.00000014 | $0.00000028 | 32,000 | 4096 | +| deepseek-coder | $0.00000014 | $0.00000028 | 16,000 | 4096 | +| groq/llama2-70b-4096 | $0.00000070 | $0.00000080 | 4,096 | 4096 | +| groq/llama3-8b-8192 | $0.00000010 | $0.00000010 | 8,192 | 8192 | +| groq/llama3-70b-8192 | $0.00000064 | $0.00000080 | 8,192 | 8192 | +| groq/mixtral-8x7b-32768 | $0.00000027 | $0.00000027 | 32,768 | 32768 | +| groq/gemma-7b-it | $0.00000010 | $0.00000010 | 8,192 | 8192 | +| claude-instant-1.2 | $0.00000016 | $0.00000055 | 100,000 | 8191 | +| claude-2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| claude-2.1 | $0.00000800 | $0.00002400 | 200,000 | 8191 | +| claude-3-haiku-20240307 | $0.00000025 | $0.00000125 | 200,000 | 4096 | +| claude-3-opus-20240229 | $0.00001500 | $0.00007500 | 200,000 | 4096 | +| claude-3-sonnet-20240229 | $0.00000300 | $0.00001500 | 200,000 | 4096 | +| text-bison | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| text-bison@001 | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| text-unicorn | $0.00001000 | $0.00002800 | 8,192 | 1024 | +| text-unicorn@001 | $0.00001000 | $0.00002800 | 8,192 | 1024 | +| chat-bison | $0.00000012 | $0.00000012 | 8,192 | 4096 | +| chat-bison@001 | $0.00000012 | $0.00000012 | 8,192 | 4096 | +| chat-bison@002 | $0.00000012 | $0.00000012 | 8,192 | 4096 | +| chat-bison-32k | $0.00000012 | $0.00000012 | 32,000 | 8192 | +| code-bison | $0.00000012 | $0.00000012 | 6,144 | 1024 | +| code-bison@001 | $0.00000012 | $0.00000012 | 6,144 | 1024 | +| code-gecko@001 | $0.00000012 | $0.00000012 | 2,048 | 64 | +| code-gecko@002 | $0.00000012 | $0.00000012 | 2,048 | 64 | +| code-gecko | $0.00000012 | $0.00000012 | 2,048 | 64 | +| codechat-bison | $0.00000012 | $0.00000012 | 6,144 | 1024 | +| codechat-bison@001 | $0.00000012 | $0.00000012 | 6,144 | 1024 | +| codechat-bison-32k | $0.00000012 | $0.00000012 | 32,000 | 8192 | +| gemini-pro | $0.00000025 | $0.00000050 | 32,760 | 8192 | +| gemini-1.0-pro | $0.00000025 | $0.00000050 | 32,760 | 8192 | +| gemini-1.0-pro-001 | $0.00000025 | $0.00000050 | 32,760 | 8192 | +| gemini-1.0-pro-002 | $0.00000025 | $0.00000050 | 32,760 | 8192 | +| gemini-1.5-pro | $0.00000063 | $0.00000188 | 1,000,000 | 8192 | +| gemini-1.5-pro-preview-0215 | $0.00000063 | $0.00000188 | 1,000,000 | 8192 | +| gemini-1.5-pro-preview-0409 | $0.00000063 | $0.00000188 | 1,000,000 | 8192 | +| gemini-experimental | $0.00000000 | $0.00000000 | 1,000,000 | 8192 | +| gemini-pro-vision | $0.00000025 | $0.00000050 | 16,384 | 2048 | +| gemini-1.0-pro-vision | $0.00000025 | $0.00000050 | 16,384 | 2048 | +| gemini-1.0-pro-vision-001 | $0.00000025 | $0.00000050 | 16,384 | 2048 | +| vertex_ai/claude-3-sonnet@20240229 | $0.00000300 | $0.00001500 | 200,000 | 4096 | +| vertex_ai/claude-3-haiku@20240307 | $0.00000025 | $0.00000125 | 200,000 | 4096 | +| vertex_ai/claude-3-opus@20240229 | $0.00000150 | $0.00000750 | 200,000 | 4096 | +| textembedding-gecko | $0.00000001 | $0.00000000 | 3,072 | nan | +| textembedding-gecko-multilingual | $0.00000001 | $0.00000000 | 3,072 | nan | +| textembedding-gecko-multilingual@001 | $0.00000001 | $0.00000000 | 3,072 | nan | +| textembedding-gecko@001 | $0.00000001 | $0.00000000 | 3,072 | nan | +| textembedding-gecko@003 | $0.00000001 | $0.00000000 | 3,072 | nan | +| text-embedding-preview-0409 | $0.00000001 | $0.00000000 | 3,072 | nan | +| text-multilingual-embedding-preview-0409 | $0.00000001 | $0.00000000 | 3,072 | nan | +| palm/chat-bison | $0.00000012 | $0.00000012 | 8,192 | 4096 | +| palm/chat-bison-001 | $0.00000012 | $0.00000012 | 8,192 | 4096 | +| palm/text-bison | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| palm/text-bison-001 | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| palm/text-bison-safety-off | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| palm/text-bison-safety-recitation-off | $0.00000012 | $0.00000012 | 8,192 | 1024 | +| gemini/gemini-pro | $0.00000000 | $0.00000000 | 32,760 | 8192 | +| gemini/gemini-1.5-pro | $0.00000000 | $0.00000000 | 1,000,000 | 8192 | +| gemini/gemini-1.5-pro-latest | $0.00000000 | $0.00000000 | 1,048,576 | 8192 | +| gemini/gemini-pro-vision | $0.00000000 | $0.00000000 | 30,720 | 2048 | +| command-r | $0.00000050 | $0.00000150 | 128,000 | 4096 | +| command-light | $0.00001500 | $0.00001500 | 4,096 | 4096 | +| command-r-plus | $0.00000300 | $0.00001500 | 128,000 | 4096 | +| command-nightly | $0.00001500 | $0.00001500 | 4,096 | 4096 | +| command | $0.00001500 | $0.00001500 | 4,096 | 4096 | +| command-medium-beta | $0.00001500 | $0.00001500 | 4,096 | 4096 | +| command-xlarge-beta | $0.00001500 | $0.00001500 | 4,096 | 4096 | +| replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1 | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| replicate/meta/llama-2-13b | $0.00000010 | $0.00000050 | 4,096 | 4096 | +| replicate/meta/llama-2-13b-chat | $0.00000010 | $0.00000050 | 4,096 | 4096 | +| replicate/meta/llama-2-70b | $0.00000065 | $0.00000275 | 4,096 | 4096 | +| replicate/meta/llama-2-70b-chat | $0.00000065 | $0.00000275 | 4,096 | 4096 | +| replicate/meta/llama-2-7b | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/meta/llama-2-7b-chat | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/meta/llama-3-70b | $0.00000065 | $0.00000275 | 4,096 | 4096 | +| replicate/meta/llama-3-70b-instruct | $0.00000065 | $0.00000275 | 4,096 | 4096 | +| replicate/meta/llama-3-8b | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/meta/llama-3-8b-instruct | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/mistralai/mistral-7b-v0.1 | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/mistralai/mistral-7b-instruct-v0.2 | $0.00000005 | $0.00000025 | 4,096 | 4096 | +| replicate/mistralai/mixtral-8x7b-instruct-v0.1 | $0.00000030 | $0.00000100 | 4,096 | 4096 | +| openrouter/microsoft/wizardlm-2-8x22b:nitro | $0.00000100 | $0.00000100 | nan | nan | +| openrouter/google/gemini-pro-1.5 | $0.00000250 | $0.00000750 | 1,000,000 | 8192 | +| openrouter/mistralai/mixtral-8x22b-instruct | $0.00000065 | $0.00000065 | nan | nan | +| openrouter/cohere/command-r-plus | $0.00000300 | $0.00001500 | nan | nan | +| openrouter/databricks/dbrx-instruct | $0.00000060 | $0.00000060 | nan | nan | +| openrouter/anthropic/claude-3-haiku | $0.00000025 | $0.00000125 | nan | nan | +| openrouter/anthropic/claude-3-sonnet | $0.00000300 | $0.00001500 | nan | nan | +| openrouter/mistralai/mistral-large | $0.00000800 | $0.00002400 | nan | nan | +| openrouter/cognitivecomputations/dolphin-mixtral-8x7b | $0.00000050 | $0.00000050 | nan | nan | +| openrouter/google/gemini-pro-vision | $0.00000012 | $0.00000038 | nan | nan | +| openrouter/fireworks/firellava-13b | $0.00000020 | $0.00000020 | nan | nan | +| openrouter/meta-llama/llama-3-8b-instruct:free | $0.00000000 | $0.00000000 | nan | nan | +| openrouter/meta-llama/llama-3-8b-instruct:extended | $0.00000022 | $0.00000225 | nan | nan | +| openrouter/meta-llama/llama-3-70b-instruct:nitro | $0.00000090 | $0.00000090 | nan | nan | +| openrouter/meta-llama/llama-3-70b-instruct | $0.00000059 | $0.00000079 | nan | nan | +| openrouter/openai/gpt-4-vision-preview | $0.00001000 | $0.00003000 | nan | nan | +| openrouter/openai/gpt-3.5-turbo | $0.00000150 | $0.00000200 | nan | nan | +| openrouter/openai/gpt-3.5-turbo-16k | $0.00000300 | $0.00000400 | nan | nan | +| openrouter/openai/gpt-4 | $0.00003000 | $0.00006000 | nan | nan | +| openrouter/anthropic/claude-instant-v1 | $0.00000163 | $0.00000551 | nan | 8191 | +| openrouter/anthropic/claude-2 | $0.00001102 | $0.00003268 | nan | 8191 | +| openrouter/anthropic/claude-3-opus | $0.00001500 | $0.00007500 | 200,000 | 4096 | +| openrouter/google/palm-2-chat-bison | $0.00000050 | $0.00000050 | nan | nan | +| openrouter/google/palm-2-codechat-bison | $0.00000050 | $0.00000050 | nan | nan | +| openrouter/meta-llama/llama-2-13b-chat | $0.00000020 | $0.00000020 | nan | nan | +| openrouter/meta-llama/llama-2-70b-chat | $0.00000150 | $0.00000150 | nan | nan | +| openrouter/meta-llama/codellama-34b-instruct | $0.00000050 | $0.00000050 | nan | nan | +| openrouter/nousresearch/nous-hermes-llama2-13b | $0.00000020 | $0.00000020 | nan | nan | +| openrouter/mancer/weaver | $0.00000563 | $0.00000563 | nan | nan | +| openrouter/gryphe/mythomax-l2-13b | $0.00000188 | $0.00000188 | nan | nan | +| openrouter/jondurbin/airoboros-l2-70b-2.1 | $0.00001388 | $0.00001388 | nan | nan | +| openrouter/undi95/remm-slerp-l2-13b | $0.00000188 | $0.00000188 | nan | nan | +| openrouter/pygmalionai/mythalion-13b | $0.00000188 | $0.00000188 | nan | nan | +| openrouter/mistralai/mistral-7b-instruct | $0.00000013 | $0.00000013 | nan | nan | +| openrouter/mistralai/mistral-7b-instruct:free | $0.00000000 | $0.00000000 | nan | nan | +| j2-ultra | $0.00001500 | $0.00001500 | 8,192 | 8192 | +| j2-mid | $0.00001000 | $0.00001000 | 8,192 | 8192 | +| j2-light | $0.00000300 | $0.00000300 | 8,192 | 8192 | +| dolphin | $0.00000050 | $0.00000050 | 16,384 | 16384 | +| chatdolphin | $0.00000050 | $0.00000050 | 16,384 | 16384 | +| luminous-base | $0.00003000 | $0.00003300 | nan | nan | +| luminous-base-control | $0.00003750 | $0.00004125 | nan | nan | +| luminous-extended | $0.00004500 | $0.00004950 | nan | nan | +| luminous-extended-control | $0.00005625 | $0.00006187 | nan | nan | +| luminous-supreme | $0.00017500 | $0.00019250 | nan | nan | +| luminous-supreme-control | $0.00021875 | $0.00024063 | nan | nan | +| ai21.j2-mid-v1 | $0.00001250 | $0.00001250 | 8,191 | 8191 | +| ai21.j2-ultra-v1 | $0.00001880 | $0.00001880 | 8,191 | 8191 | +| amazon.titan-text-lite-v1 | $0.00000030 | $0.00000040 | 42,000 | 4000 | +| amazon.titan-text-express-v1 | $0.00000130 | $0.00000170 | 42,000 | 8000 | +| amazon.titan-embed-text-v1 | $0.00000010 | $0.00000000 | 8,192 | nan | +| amazon.titan-embed-text-v2:0 | $0.00000020 | $0.00000000 | 8,192 | nan | +| mistral.mistral-7b-instruct-v0:2 | $0.00000015 | $0.00000020 | 32,000 | 8191 | +| mistral.mixtral-8x7b-instruct-v0:1 | $0.00000045 | $0.00000070 | 32,000 | 8191 | +| mistral.mistral-large-2402-v1:0 | $0.00000800 | $0.00002400 | 32,000 | 8191 | +| bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1 | $0.00000045 | $0.00000070 | 32,000 | 8191 | +| bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1 | $0.00000045 | $0.00000070 | 32,000 | 8191 | +| bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1 | $0.00000059 | $0.00000091 | 32,000 | 8191 | +| bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2 | $0.00000015 | $0.00000020 | 32,000 | 8191 | +| bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2 | $0.00000015 | $0.00000020 | 32,000 | 8191 | +| bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2 | $0.00000020 | $0.00000026 | 32,000 | 8191 | +| bedrock/us-east-1/mistral.mistral-large-2402-v1:0 | $0.00000800 | $0.00002400 | 32,000 | 8191 | +| bedrock/us-west-2/mistral.mistral-large-2402-v1:0 | $0.00000800 | $0.00002400 | 32,000 | 8191 | +| bedrock/eu-west-3/mistral.mistral-large-2402-v1:0 | $0.00001040 | $0.00003120 | 32,000 | 8191 | +| anthropic.claude-3-sonnet-20240229-v1:0 | $0.00000300 | $0.00001500 | 200,000 | 4096 | +| anthropic.claude-3-haiku-20240307-v1:0 | $0.00000025 | $0.00000125 | 200,000 | 4096 | +| anthropic.claude-3-opus-20240229-v1:0 | $0.00001500 | $0.00007500 | 200,000 | 4096 | +| anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-east-1/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-west-2/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/anthropic.claude-v1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/1-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/6-month-commitment/anthropic.claude-v1 | -- | -- | 100,000 | 8191 | +| anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-east-1/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-west-2/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/anthropic.claude-v2 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/1-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/6-month-commitment/anthropic.claude-v2 | -- | -- | 100,000 | 8191 | +| anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-east-1/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/us-west-2/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/anthropic.claude-v2:1 | $0.00000800 | $0.00002400 | 100,000 | 8191 | +| bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1 | -- | -- | 100,000 | 8191 | +| anthropic.claude-instant-v1 | $0.00000163 | $0.00000551 | 100,000 | 8191 | +| bedrock/us-east-1/anthropic.claude-instant-v1 | $0.00000080 | $0.00000240 | 100,000 | 8191 | +| bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/us-west-2/anthropic.claude-instant-v1 | $0.00000080 | $0.00000240 | 100,000 | 8191 | +| bedrock/ap-northeast-1/anthropic.claude-instant-v1 | $0.00000223 | $0.00000755 | 100,000 | 8191 | +| bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/anthropic.claude-instant-v1 | $0.00000248 | $0.00000838 | 100,000 | 8191 | +| bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1 | -- | -- | 100,000 | 8191 | +| cohere.command-text-v14 | $0.00000150 | $0.00000200 | 4,096 | 4096 | +| bedrock/*/1-month-commitment/cohere.command-text-v14 | -- | -- | 4,096 | 4096 | +| bedrock/*/6-month-commitment/cohere.command-text-v14 | -- | -- | 4,096 | 4096 | +| cohere.command-light-text-v14 | $0.00000030 | $0.00000060 | 4,096 | 4096 | +| bedrock/*/1-month-commitment/cohere.command-light-text-v14 | -- | -- | 4,096 | 4096 | +| bedrock/*/6-month-commitment/cohere.command-light-text-v14 | -- | -- | 4,096 | 4096 | +| cohere.command-r-plus-v1:0 | $0.00000300 | $0.00001500 | 128,000 | 4096 | +| cohere.command-r-v1:0 | $0.00000050 | $0.00000150 | 128,000 | 4096 | +| cohere.embed-english-v3 | $0.00000010 | $0.00000000 | 512 | nan | +| cohere.embed-multilingual-v3 | $0.00000010 | $0.00000000 | 512 | nan | +| meta.llama2-13b-chat-v1 | $0.00000075 | $0.00000100 | 4,096 | 4096 | +| meta.llama2-70b-chat-v1 | $0.00000195 | $0.00000256 | 4,096 | 4096 | +| meta.llama3-8b-instruct-v1:0 | $0.00000040 | $0.00000060 | 8,192 | 8192 | +| meta.llama3-70b-instruct-v1:0 | $0.00000265 | $0.00000350 | 8,192 | 8192 | +| 512-x-512/50-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan | +| 512-x-512/max-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan | +| max-x-max/50-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan | +| max-x-max/max-steps/stability.stable-diffusion-xl-v0 | -- | -- | 77 | nan | +| 1024-x-1024/50-steps/stability.stable-diffusion-xl-v1 | -- | -- | 77 | nan | +| 1024-x-1024/max-steps/stability.stable-diffusion-xl-v1 | -- | -- | 77 | nan | +| sagemaker/meta-textgeneration-llama-2-7b | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| sagemaker/meta-textgeneration-llama-2-7b-f | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| sagemaker/meta-textgeneration-llama-2-13b | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| sagemaker/meta-textgeneration-llama-2-13b-f | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| sagemaker/meta-textgeneration-llama-2-70b | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| sagemaker/meta-textgeneration-llama-2-70b-b-f | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| together-ai-up-to-3b | $0.00000010 | $0.00000010 | nan | nan | +| together-ai-3.1b-7b | $0.00000020 | $0.00000020 | nan | nan | +| together-ai-7.1b-20b | $0.00000040 | $0.00000040 | nan | nan | +| together-ai-20.1b-40b | $0.00000080 | $0.00000080 | nan | nan | +| together-ai-40.1b-70b | $0.00000090 | $0.00000090 | nan | nan | +| together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1 | $0.00000060 | $0.00000060 | nan | nan | +| together_ai/mistralai/Mistral-7B-Instruct-v0.1 | -- | -- | nan | nan | +| together_ai/togethercomputer/CodeLlama-34b-Instruct | -- | -- | nan | nan | +| ollama/llama2 | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/llama2:13b | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/llama2:70b | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/llama2-uncensored | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/mistral | $0.00000000 | $0.00000000 | 8,192 | 8192 | +| ollama/codellama | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/orca-mini | $0.00000000 | $0.00000000 | 4,096 | 4096 | +| ollama/vicuna | $0.00000000 | $0.00000000 | 2,048 | 2048 | +| deepinfra/lizpreciatior/lzlv_70b_fp16_hf | $0.00000070 | $0.00000090 | 4,096 | 4096 | +| deepinfra/Gryphe/MythoMax-L2-13b | $0.00000022 | $0.00000022 | 4,096 | 4096 | +| deepinfra/mistralai/Mistral-7B-Instruct-v0.1 | $0.00000013 | $0.00000013 | 32,768 | 8191 | +| deepinfra/meta-llama/Llama-2-70b-chat-hf | $0.00000070 | $0.00000090 | 4,096 | 4096 | +| deepinfra/cognitivecomputations/dolphin-2.6-mixtral-8x7b | $0.00000027 | $0.00000027 | 32,768 | 8191 | +| deepinfra/codellama/CodeLlama-34b-Instruct-hf | $0.00000060 | $0.00000060 | 4,096 | 4096 | +| deepinfra/deepinfra/mixtral | $0.00000027 | $0.00000027 | 32,000 | 4096 | +| deepinfra/Phind/Phind-CodeLlama-34B-v2 | $0.00000060 | $0.00000060 | 16,384 | 4096 | +| deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1 | $0.00000027 | $0.00000027 | 32,768 | 8191 | +| deepinfra/deepinfra/airoboros-70b | $0.00000070 | $0.00000090 | 4,096 | 4096 | +| deepinfra/01-ai/Yi-34B-Chat | $0.00000060 | $0.00000060 | 4,096 | 4096 | +| deepinfra/01-ai/Yi-6B-200K | $0.00000013 | $0.00000013 | 200,000 | 4096 | +| deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1 | $0.00000070 | $0.00000090 | 4,096 | 4096 | +| deepinfra/meta-llama/Llama-2-13b-chat-hf | $0.00000022 | $0.00000022 | 4,096 | 4096 | +| deepinfra/amazon/MistralLite | $0.00000020 | $0.00000020 | 32,768 | 8191 | +| deepinfra/meta-llama/Llama-2-7b-chat-hf | $0.00000013 | $0.00000013 | 4,096 | 4096 | +| deepinfra/01-ai/Yi-34B-200K | $0.00000060 | $0.00000060 | 200,000 | 4096 | +| deepinfra/openchat/openchat_3.5 | $0.00000013 | $0.00000013 | 4,096 | 4096 | +| perplexity/codellama-34b-instruct | $0.00000035 | $0.00000140 | 16,384 | 16384 | +| perplexity/codellama-70b-instruct | $0.00000070 | $0.00000280 | 16,384 | 16384 | +| perplexity/pplx-7b-chat | $0.00000007 | $0.00000028 | 8,192 | 8192 | +| perplexity/pplx-70b-chat | $0.00000070 | $0.00000280 | 4,096 | 4096 | +| perplexity/pplx-7b-online | $0.00000000 | $0.00000028 | 4,096 | 4096 | +| perplexity/pplx-70b-online | $0.00000000 | $0.00000280 | 4,096 | 4096 | +| perplexity/llama-2-70b-chat | $0.00000070 | $0.00000280 | 4,096 | 4096 | +| perplexity/mistral-7b-instruct | $0.00000007 | $0.00000028 | 4,096 | 4096 | +| perplexity/mixtral-8x7b-instruct | $0.00000007 | $0.00000028 | 4,096 | 4096 | +| perplexity/sonar-small-chat | $0.00000007 | $0.00000028 | 16,384 | 16384 | +| perplexity/sonar-small-online | $0.00000000 | $0.00000028 | 12,000 | 12000 | +| perplexity/sonar-medium-chat | $0.00000060 | $0.00000180 | 16,384 | 16384 | +| perplexity/sonar-medium-online | $0.00000000 | $0.00000180 | 12,000 | 12000 | +| anyscale/mistralai/Mistral-7B-Instruct-v0.1 | $0.00000015 | $0.00000015 | 16,384 | 16384 | +| anyscale/Mixtral-8x7B-Instruct-v0.1 | $0.00000015 | $0.00000015 | 16,384 | 16384 | +| anyscale/HuggingFaceH4/zephyr-7b-beta | $0.00000015 | $0.00000015 | 16,384 | 16384 | +| anyscale/meta-llama/Llama-2-7b-chat-hf | $0.00000015 | $0.00000015 | 4,096 | 4096 | +| anyscale/meta-llama/Llama-2-13b-chat-hf | $0.00000025 | $0.00000025 | 4,096 | 4096 | +| anyscale/meta-llama/Llama-2-70b-chat-hf | $0.00000100 | $0.00000100 | 4,096 | 4096 | +| anyscale/codellama/CodeLlama-34b-Instruct-hf | $0.00000100 | $0.00000100 | 4,096 | 4096 | +| cloudflare/@cf/meta/llama-2-7b-chat-fp16 | $0.00000192 | $0.00000192 | 3,072 | 3072 | +| cloudflare/@cf/meta/llama-2-7b-chat-int8 | $0.00000192 | $0.00000192 | 2,048 | 2048 | +| cloudflare/@cf/mistral/mistral-7b-instruct-v0.1 | $0.00000192 | $0.00000192 | 8,192 | 8192 | +| cloudflare/@hf/thebloke/codellama-7b-instruct-awq | $0.00000192 | $0.00000192 | 4,096 | 4096 | +| voyage/voyage-01 | $0.00000010 | $0.00000000 | 4,096 | nan | +| voyage/voyage-lite-01 | $0.00000010 | $0.00000000 | 4,096 | nan | +| voyage/voyage-large-2 | $0.00000012 | $0.00000000 | 16,000 | nan | +| voyage/voyage-law-2 | $0.00000012 | $0.00000000 | 16,000 | nan | +| voyage/voyage-code-2 | $0.00000012 | $0.00000000 | 16,000 | nan | +| voyage/voyage-2 | $0.00000010 | $0.00000000 | 4,000 | nan | +| voyage/voyage-lite-02-instruct | $0.00000010 | $0.00000000 | 4,000 | nan | \ No newline at end of file diff --git a/print_table.py b/print_table.py deleted file mode 100644 index 0973b52..0000000 --- a/print_table.py +++ /dev/null @@ -1,27 +0,0 @@ -import pandas as pd -import tokencost - -# Load the data -df = pd.DataFrame(tokencost.TOKEN_COSTS).T -df['max_input_tokens'] = df['max_input_tokens'].apply(lambda x: '{:,.0f}'.format(x)) -df['max_tokens'] = df['max_tokens'].apply(lambda x: '{:,.0f}'.format(x)) - - -# Updated function to format the cost or handle NaN - - -def format_cost(x): - if pd.isna(x): - return '--' - else: - # Ensure the number is treated as a float and format it - return '${:.8f}'.format(float(x)) - - -# Apply the formatting function -df[['input_cost_per_token', 'output_cost_per_token']] = df[[ - 'input_cost_per_token', 'output_cost_per_token']].applymap(format_cost) - -# Write the DataFrame as markdown to a file -with open('pricing_table.md', 'w') as f: - f.write(df[['max_tokens', 'max_input_tokens', 'input_cost_per_token', 'output_cost_per_token']].to_markdown()) diff --git a/tokencost/model_prices.json b/tokencost/model_prices.json index c2c172b..6379dae 100644 --- a/tokencost/model_prices.json +++ b/tokencost/model_prices.json @@ -1,20 +1,44 @@ { "gpt-4": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 0.00003, - "output_cost_per_token": 0.00006, + "max_output_tokens": 4096, + "input_cost_per_token": 3e-05, + "output_cost_per_token": 6e-05, "litellm_provider": "openai", "mode": "chat", "supports_function_calling": true }, + "gpt-4o": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true + }, + "gpt-4o-2024-05-13": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true + }, "gpt-4-turbo-preview": { "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00003, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, "litellm_provider": "openai", "mode": "chat", "supports_function_calling": true, @@ -24,8 +48,8 @@ "max_tokens": 4096, "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 0.00003, - "output_cost_per_token": 0.00006, + "input_cost_per_token": 3e-05, + "output_cost_per_token": 6e-05, "litellm_provider": "openai", "mode": "chat" }, @@ -33,8 +57,8 @@ "max_tokens": 4096, "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 0.00003, - "output_cost_per_token": 0.00006, + "input_cost_per_token": 3e-05, + "output_cost_per_token": 6e-05, "litellm_provider": "openai", "mode": "chat", "supports_function_calling": true @@ -43,7 +67,7 @@ "max_tokens": 4096, "max_input_tokens": 32768, "max_output_tokens": 4096, - "input_cost_per_token": 0.00006, + "input_cost_per_token": 6e-05, "output_cost_per_token": 0.00012, "litellm_provider": "openai", "mode": "chat" @@ -52,7 +76,7 @@ "max_tokens": 4096, "max_input_tokens": 32768, "max_output_tokens": 4096, - "input_cost_per_token": 0.00006, + "input_cost_per_token": 6e-05, "output_cost_per_token": 0.00012, "litellm_provider": "openai", "mode": "chat" @@ -61,7 +85,7 @@ "max_tokens": 4096, "max_input_tokens": 32768, "max_output_tokens": 4096, - "input_cost_per_token": 0.00006, + "input_cost_per_token": 6e-05, "output_cost_per_token": 0.00012, "litellm_provider": "openai", "mode": "chat" @@ -70,8 +94,8 @@ "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00003, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, "litellm_provider": "openai", "mode": "chat", "supports_function_calling": true, @@ -82,8 +106,8 @@ "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00003, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, "litellm_provider": "openai", "mode": "chat", "supports_function_calling": true, @@ -94,8 +118,8 @@ "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00003, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, "litellm_provider": "openai", "mode": "chat", "supports_function_calling": true, @@ -105,8 +129,8 @@ "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00003, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, "litellm_provider": "openai", "mode": "chat", "supports_function_calling": true, @@ -116,8 +140,8 @@ "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00003, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, "litellm_provider": "openai", "mode": "chat", "supports_vision": true @@ -126,8 +150,8 @@ "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00003, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, "litellm_provider": "openai", "mode": "chat", "supports_vision": true @@ -136,8 +160,8 @@ "max_tokens": 4097, "max_input_tokens": 16385, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000002, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "openai", "mode": "chat", "supports_function_calling": true @@ -146,8 +170,8 @@ "max_tokens": 4097, "max_input_tokens": 4097, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000002, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "openai", "mode": "chat" }, @@ -155,8 +179,8 @@ "max_tokens": 4097, "max_input_tokens": 4097, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000002, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "openai", "mode": "chat", "supports_function_calling": true @@ -165,8 +189,8 @@ "max_tokens": 16385, "max_input_tokens": 16385, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000010, - "output_cost_per_token": 0.0000020, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "openai", "mode": "chat", "supports_function_calling": true, @@ -176,8 +200,8 @@ "max_tokens": 16385, "max_input_tokens": 16385, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000005, - "output_cost_per_token": 0.0000015, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, "litellm_provider": "openai", "mode": "chat", "supports_function_calling": true, @@ -187,8 +211,8 @@ "max_tokens": 16385, "max_input_tokens": 16385, "max_output_tokens": 4096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000004, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 4e-06, "litellm_provider": "openai", "mode": "chat" }, @@ -196,8 +220,8 @@ "max_tokens": 16385, "max_input_tokens": 16385, "max_output_tokens": 4096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000004, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 4e-06, "litellm_provider": "openai", "mode": "chat" }, @@ -205,8 +229,8 @@ "max_tokens": 4097, "max_input_tokens": 4097, "max_output_tokens": 4096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000006, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 6e-06, "litellm_provider": "openai", "mode": "chat" }, @@ -214,34 +238,34 @@ "max_tokens": 8191, "max_input_tokens": 8191, "output_vector_size": 3072, - "input_cost_per_token": 0.00000013, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 0.0, "litellm_provider": "openai", "mode": "embedding" }, "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, + "output_vector_size": 1536, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 0.0, "litellm_provider": "openai", "mode": "embedding" }, "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, + "output_vector_size": 1536, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, "litellm_provider": "openai", "mode": "embedding" }, "text-embedding-ada-002-v2": { "max_tokens": 8191, "max_input_tokens": 8191, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, "litellm_provider": "openai", "mode": "embedding" }, @@ -249,8 +273,8 @@ "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 0, - "input_cost_per_token": 0.000000, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, "litellm_provider": "openai", "mode": "moderations" }, @@ -258,8 +282,8 @@ "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 0, - "input_cost_per_token": 0.000000, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, "litellm_provider": "openai", "mode": "moderations" }, @@ -267,83 +291,95 @@ "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 0, - "input_cost_per_token": 0.000000, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, "litellm_provider": "openai", "mode": "moderations" }, "256-x-256/dall-e-2": { "mode": "image_generation", - "input_cost_per_pixel": 0.00000024414, + "input_cost_per_pixel": 2.4414e-07, "output_cost_per_pixel": 0.0, "litellm_provider": "openai" }, "512-x-512/dall-e-2": { "mode": "image_generation", - "input_cost_per_pixel": 0.0000000686, + "input_cost_per_pixel": 6.86e-08, "output_cost_per_pixel": 0.0, "litellm_provider": "openai" }, "1024-x-1024/dall-e-2": { "mode": "image_generation", - "input_cost_per_pixel": 0.000000019, + "input_cost_per_pixel": 1.9e-08, "output_cost_per_pixel": 0.0, "litellm_provider": "openai" }, "hd/1024-x-1792/dall-e-3": { "mode": "image_generation", - "input_cost_per_pixel": 0.00000006539, + "input_cost_per_pixel": 6.539e-08, "output_cost_per_pixel": 0.0, "litellm_provider": "openai" }, "hd/1792-x-1024/dall-e-3": { "mode": "image_generation", - "input_cost_per_pixel": 0.00000006539, + "input_cost_per_pixel": 6.539e-08, "output_cost_per_pixel": 0.0, "litellm_provider": "openai" }, "hd/1024-x-1024/dall-e-3": { "mode": "image_generation", - "input_cost_per_pixel": 0.00000007629, + "input_cost_per_pixel": 7.629e-08, "output_cost_per_pixel": 0.0, "litellm_provider": "openai" }, "standard/1024-x-1792/dall-e-3": { "mode": "image_generation", - "input_cost_per_pixel": 0.00000004359, + "input_cost_per_pixel": 4.359e-08, "output_cost_per_pixel": 0.0, "litellm_provider": "openai" }, "standard/1792-x-1024/dall-e-3": { "mode": "image_generation", - "input_cost_per_pixel": 0.00000004359, + "input_cost_per_pixel": 4.359e-08, "output_cost_per_pixel": 0.0, "litellm_provider": "openai" }, "standard/1024-x-1024/dall-e-3": { "mode": "image_generation", - "input_cost_per_pixel": 0.0000000381469, + "input_cost_per_pixel": 3.81469e-08, "output_cost_per_pixel": 0.0, "litellm_provider": "openai" }, "whisper-1": { "mode": "audio_transcription", "input_cost_per_second": 0, - "output_cost_per_second": 0.0001, + "output_cost_per_second": 0.0001, "litellm_provider": "openai" - }, + }, "azure/whisper-1": { "mode": "audio_transcription", - "input_cost_per_second": 0, - "output_cost_per_second": 0.0001, + "input_cost_per_second": 0, + "output_cost_per_second": 0.0001, "litellm_provider": "azure" }, + "azure/gpt-4-turbo-2024-04-09": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_vision": true + }, "azure/gpt-4-0125-preview": { "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00003, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -353,8 +389,8 @@ "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00003, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -364,8 +400,8 @@ "max_tokens": 4096, "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 0.00003, - "output_cost_per_token": 0.00006, + "input_cost_per_token": 3e-05, + "output_cost_per_token": 6e-05, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true @@ -374,7 +410,7 @@ "max_tokens": 4096, "max_input_tokens": 32768, "max_output_tokens": 4096, - "input_cost_per_token": 0.00006, + "input_cost_per_token": 6e-05, "output_cost_per_token": 0.00012, "litellm_provider": "azure", "mode": "chat" @@ -383,7 +419,7 @@ "max_tokens": 4096, "max_input_tokens": 32768, "max_output_tokens": 4096, - "input_cost_per_token": 0.00006, + "input_cost_per_token": 6e-05, "output_cost_per_token": 0.00012, "litellm_provider": "azure", "mode": "chat" @@ -392,8 +428,8 @@ "max_tokens": 4096, "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 0.00003, - "output_cost_per_token": 0.00006, + "input_cost_per_token": 3e-05, + "output_cost_per_token": 6e-05, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true @@ -402,9 +438,9 @@ "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": "azure", + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, + "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -413,9 +449,9 @@ "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": "azure", + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, + "litellm_provider": "azure", "mode": "chat", "supports_vision": true }, @@ -423,8 +459,8 @@ "max_tokens": 4096, "max_input_tokens": 16385, "max_output_tokens": 4096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000004, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 4e-06, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true @@ -433,8 +469,8 @@ "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000002, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -444,8 +480,8 @@ "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000005, - "output_cost_per_token": 0.0000015, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -455,8 +491,8 @@ "max_tokens": 4096, "max_input_tokens": 16385, "max_output_tokens": 4096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000004, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 4e-06, "litellm_provider": "azure", "mode": "chat" }, @@ -464,8 +500,8 @@ "max_tokens": 4096, "max_input_tokens": 4097, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000002, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true @@ -473,24 +509,24 @@ "azure/gpt-3.5-turbo-instruct-0914": { "max_tokens": 4097, "max_input_tokens": 4097, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000002, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "text-completion-openai", "mode": "completion" }, "azure/gpt-35-turbo-instruct": { "max_tokens": 4097, "max_input_tokens": 4097, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000002, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "text-completion-openai", "mode": "completion" }, "azure/mistral-large-latest": { "max_tokens": 32000, "max_input_tokens": 32000, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true @@ -498,18 +534,18 @@ "azure/mistral-large-2402": { "max_tokens": 32000, "max_input_tokens": 32000, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true }, "azure/command-r-plus": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true @@ -517,83 +553,83 @@ "azure/ada": { "max_tokens": 8191, "max_input_tokens": 8191, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, "litellm_provider": "azure", "mode": "embedding" }, "azure/text-embedding-ada-002": { "max_tokens": 8191, "max_input_tokens": 8191, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, "litellm_provider": "azure", "mode": "embedding" }, "azure/text-embedding-3-large": { "max_tokens": 8191, "max_input_tokens": 8191, - "input_cost_per_token": 0.00000013, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 0.0, "litellm_provider": "azure", "mode": "embedding" }, "azure/text-embedding-3-small": { "max_tokens": 8191, "max_input_tokens": 8191, - "input_cost_per_token": 0.00000002, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 0.0, "litellm_provider": "azure", "mode": "embedding" - }, + }, "azure/standard/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 0.0000000381469, + "input_cost_per_pixel": 3.81469e-08, "output_cost_per_token": 0.0, - "litellm_provider": "azure", + "litellm_provider": "azure", "mode": "image_generation" }, "azure/hd/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 0.00000007629, + "input_cost_per_pixel": 7.629e-08, "output_cost_per_token": 0.0, - "litellm_provider": "azure", + "litellm_provider": "azure", "mode": "image_generation" }, "azure/standard/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 0.00000004359, + "input_cost_per_pixel": 4.359e-08, "output_cost_per_token": 0.0, - "litellm_provider": "azure", + "litellm_provider": "azure", "mode": "image_generation" }, "azure/standard/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 0.00000004359, + "input_cost_per_pixel": 4.359e-08, "output_cost_per_token": 0.0, - "litellm_provider": "azure", + "litellm_provider": "azure", "mode": "image_generation" }, "azure/hd/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 0.00000006539, + "input_cost_per_pixel": 6.539e-08, "output_cost_per_token": 0.0, - "litellm_provider": "azure", + "litellm_provider": "azure", "mode": "image_generation" }, "azure/hd/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 0.00000006539, + "input_cost_per_pixel": 6.539e-08, "output_cost_per_token": 0.0, - "litellm_provider": "azure", + "litellm_provider": "azure", "mode": "image_generation" }, "azure/standard/1024-x-1024/dall-e-2": { "input_cost_per_pixel": 0.0, "output_cost_per_token": 0.0, - "litellm_provider": "azure", + "litellm_provider": "azure", "mode": "image_generation" }, "babbage-002": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000004, - "output_cost_per_token": 0.0000004, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "text-completion-openai", "mode": "completion" }, @@ -601,17 +637,17 @@ "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 4096, - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000002, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "text-completion-openai", "mode": "completion" - }, + }, "gpt-3.5-turbo-instruct": { "max_tokens": 4096, "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000002, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "text-completion-openai", "mode": "completion" }, @@ -619,18 +655,17 @@ "max_tokens": 4097, "max_input_tokens": 8192, "max_output_tokens": 4097, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000002, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "text-completion-openai", "mode": "completion" - }, "claude-instant-1": { "max_tokens": 8191, "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000163, - "output_cost_per_token": 0.00000551, + "input_cost_per_token": 1.63e-06, + "output_cost_per_token": 5.51e-06, "litellm_provider": "anthropic", "mode": "chat" }, @@ -638,8 +673,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000015, - "output_cost_per_token": 0.00000046, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 4.6e-07, "litellm_provider": "mistral", "mode": "chat" }, @@ -647,26 +682,28 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000006, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, "litellm_provider": "mistral", + "supports_function_calling": true, "mode": "chat" }, "mistral/mistral-small-latest": { "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000006, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, "litellm_provider": "mistral", + "supports_function_calling": true, "mode": "chat" }, "mistral/mistral-medium": { "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.0000027, - "output_cost_per_token": 0.0000081, + "input_cost_per_token": 2.7e-06, + "output_cost_per_token": 8.1e-06, "litellm_provider": "mistral", "mode": "chat" }, @@ -674,8 +711,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.0000027, - "output_cost_per_token": 0.0000081, + "input_cost_per_token": 2.7e-06, + "output_cost_per_token": 8.1e-06, "litellm_provider": "mistral", "mode": "chat" }, @@ -683,8 +720,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.0000027, - "output_cost_per_token": 0.0000081, + "input_cost_per_token": 2.7e-06, + "output_cost_per_token": 8.1e-06, "litellm_provider": "mistral", "mode": "chat" }, @@ -692,8 +729,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "mistral", "mode": "chat", "supports_function_calling": true @@ -702,8 +739,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "mistral", "mode": "chat", "supports_function_calling": true @@ -712,8 +749,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000002, - "output_cost_per_token": 0.000006, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, "litellm_provider": "mistral", "mode": "chat", "supports_function_calling": true @@ -721,16 +758,34 @@ "mistral/mistral-embed": { "max_tokens": 8192, "max_input_tokens": 8192, - "input_cost_per_token": 0.000000111, + "input_cost_per_token": 1.11e-07, "litellm_provider": "mistral", "mode": "embedding" }, + "deepseek-chat": { + "max_tokens": 4096, + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "deepseek", + "mode": "chat" + }, + "deepseek-coder": { + "max_tokens": 4096, + "max_input_tokens": 16000, + "max_output_tokens": 4096, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "deepseek", + "mode": "chat" + }, "groq/llama2-70b-4096": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000070, - "output_cost_per_token": 0.00000080, + "input_cost_per_token": 7e-07, + "output_cost_per_token": 8e-07, "litellm_provider": "groq", "mode": "chat", "supports_function_calling": true @@ -739,8 +794,8 @@ "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000010, - "output_cost_per_token": 0.00000010, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1e-07, "litellm_provider": "groq", "mode": "chat", "supports_function_calling": true @@ -749,8 +804,8 @@ "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000064, - "output_cost_per_token": 0.00000080, + "input_cost_per_token": 6.4e-07, + "output_cost_per_token": 8e-07, "litellm_provider": "groq", "mode": "chat", "supports_function_calling": true @@ -759,8 +814,8 @@ "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, - "input_cost_per_token": 0.00000027, - "output_cost_per_token": 0.00000027, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 2.7e-07, "litellm_provider": "groq", "mode": "chat", "supports_function_calling": true @@ -769,8 +824,8 @@ "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000010, - "output_cost_per_token": 0.00000010, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1e-07, "litellm_provider": "groq", "mode": "chat", "supports_function_calling": true @@ -779,8 +834,8 @@ "max_tokens": 8191, "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000000163, - "output_cost_per_token": 0.000000551, + "input_cost_per_token": 1.63e-07, + "output_cost_per_token": 5.51e-07, "litellm_provider": "anthropic", "mode": "chat" }, @@ -788,8 +843,8 @@ "max_tokens": 8191, "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "anthropic", "mode": "chat" }, @@ -797,8 +852,8 @@ "max_tokens": 8191, "max_input_tokens": 200000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "anthropic", "mode": "chat" }, @@ -806,35 +861,44 @@ "max_tokens": 4096, "max_input_tokens": 200000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.00000125, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.25e-06, "litellm_provider": "anthropic", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 264 }, "claude-3-opus-20240229": { "max_tokens": 4096, "max_input_tokens": 200000, "max_output_tokens": 4096, - "input_cost_per_token": 0.000015, - "output_cost_per_token": 0.000075, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 7.5e-05, "litellm_provider": "anthropic", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395 }, "claude-3-sonnet-20240229": { "max_tokens": 4096, "max_input_tokens": 200000, "max_output_tokens": 4096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, "litellm_provider": "anthropic", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, "text-bison": { "max_tokens": 1024, "max_input_tokens": 8192, "max_output_tokens": 1024, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-text-models", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -843,8 +907,8 @@ "max_tokens": 1024, "max_input_tokens": 8192, "max_output_tokens": 1024, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-text-models", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -853,8 +917,8 @@ "max_tokens": 1024, "max_input_tokens": 8192, "max_output_tokens": 1024, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.000028, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 2.8e-05, "litellm_provider": "vertex_ai-text-models", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -863,8 +927,8 @@ "max_tokens": 1024, "max_input_tokens": 8192, "max_output_tokens": 1024, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.000028, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 2.8e-05, "litellm_provider": "vertex_ai-text-models", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -873,8 +937,8 @@ "max_tokens": 4096, "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-chat-models", "mode": "chat", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -883,8 +947,8 @@ "max_tokens": 4096, "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-chat-models", "mode": "chat", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -893,8 +957,8 @@ "max_tokens": 4096, "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-chat-models", "mode": "chat", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -903,8 +967,8 @@ "max_tokens": 8192, "max_input_tokens": 32000, "max_output_tokens": 8192, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-chat-models", "mode": "chat", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -913,8 +977,8 @@ "max_tokens": 1024, "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", "mode": "chat", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -923,8 +987,8 @@ "max_tokens": 1024, "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -933,8 +997,8 @@ "max_tokens": 64, "max_input_tokens": 2048, "max_output_tokens": 64, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -943,8 +1007,8 @@ "max_tokens": 64, "max_input_tokens": 2048, "max_output_tokens": 64, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -953,8 +1017,8 @@ "max_tokens": 64, "max_input_tokens": 2048, "max_output_tokens": 64, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -963,8 +1027,8 @@ "max_tokens": 1024, "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-chat-models", "mode": "chat", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -973,8 +1037,8 @@ "max_tokens": 1024, "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-chat-models", "mode": "chat", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -983,8 +1047,8 @@ "max_tokens": 8192, "max_input_tokens": 32000, "max_output_tokens": 8192, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-chat-models", "mode": "chat", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -993,80 +1057,80 @@ "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-language-models", "mode": "chat", "supports_function_calling": true, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "gemini-1.0-pro": { + "gemini-1.0-pro": { "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-language-models", "mode": "chat", "supports_function_calling": true, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "gemini-1.0-pro-001": { + "gemini-1.0-pro-001": { "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-language-models", "mode": "chat", "supports_function_calling": true, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "gemini-1.0-pro-002": { + "gemini-1.0-pro-002": { "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-language-models", "mode": "chat", "supports_function_calling": true, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "gemini-1.5-pro": { + "gemini-1.5-pro": { "max_tokens": 8192, "max_input_tokens": 1000000, "max_output_tokens": 8192, - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "input_cost_per_token": 6.25e-07, + "output_cost_per_token": 1.875e-06, "litellm_provider": "vertex_ai-language-models", "mode": "chat", "supports_function_calling": true, - "supports_tool_choice": 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": { + "gemini-1.5-pro-preview-0215": { "max_tokens": 8192, "max_input_tokens": 1000000, "max_output_tokens": 8192, - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "input_cost_per_token": 6.25e-07, + "output_cost_per_token": 1.875e-06, "litellm_provider": "vertex_ai-language-models", "mode": "chat", "supports_function_calling": true, - "supports_tool_choice": 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": { "max_tokens": 8192, "max_input_tokens": 1000000, "max_output_tokens": 8192, - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "input_cost_per_token": 6.25e-07, + "output_cost_per_token": 1.875e-06, "litellm_provider": "vertex_ai-language-models", "mode": "chat", "supports_function_calling": true, - "supports_tool_choice": true, + "supports_tool_choice": true, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "gemini-experimental": { @@ -1078,7 +1142,7 @@ "litellm_provider": "vertex_ai-language-models", "mode": "chat", "supports_function_calling": false, - "supports_tool_choice": true, + "supports_tool_choice": true, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "gemini-pro-vision": { @@ -1088,8 +1152,8 @@ "max_images_per_prompt": 16, "max_videos_per_prompt": 1, "max_video_length": 2, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-vision-models", "mode": "chat", "supports_function_calling": true, @@ -1103,8 +1167,8 @@ "max_images_per_prompt": 16, "max_videos_per_prompt": 1, "max_video_length": 2, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-vision-models", "mode": "chat", "supports_function_calling": true, @@ -1118,8 +1182,8 @@ "max_images_per_prompt": 16, "max_videos_per_prompt": 1, "max_video_length": 2, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "vertex_ai-vision-models", "mode": "chat", "supports_function_calling": true, @@ -1130,34 +1194,40 @@ "max_tokens": 4096, "max_input_tokens": 200000, "max_output_tokens": 4096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true }, "vertex_ai/claude-3-haiku@20240307": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 200000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.00000125, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.25e-06, "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true }, "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, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 7.5e-06, "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true }, "textembedding-gecko": { "max_tokens": 3072, "max_input_tokens": 3072, "output_vector_size": 768, - "input_cost_per_token": 0.00000000625, + "input_cost_per_token": 6.25e-09, "output_cost_per_token": 0, "litellm_provider": "vertex_ai-embedding-models", "mode": "embedding", @@ -1167,7 +1237,7 @@ "max_tokens": 3072, "max_input_tokens": 3072, "output_vector_size": 768, - "input_cost_per_token": 0.00000000625, + "input_cost_per_token": 6.25e-09, "output_cost_per_token": 0, "litellm_provider": "vertex_ai-embedding-models", "mode": "embedding", @@ -1177,7 +1247,7 @@ "max_tokens": 3072, "max_input_tokens": 3072, "output_vector_size": 768, - "input_cost_per_token": 0.00000000625, + "input_cost_per_token": 6.25e-09, "output_cost_per_token": 0, "litellm_provider": "vertex_ai-embedding-models", "mode": "embedding", @@ -1187,7 +1257,7 @@ "max_tokens": 3072, "max_input_tokens": 3072, "output_vector_size": 768, - "input_cost_per_token": 0.00000000625, + "input_cost_per_token": 6.25e-09, "output_cost_per_token": 0, "litellm_provider": "vertex_ai-embedding-models", "mode": "embedding", @@ -1197,7 +1267,7 @@ "max_tokens": 3072, "max_input_tokens": 3072, "output_vector_size": 768, - "input_cost_per_token": 0.00000000625, + "input_cost_per_token": 6.25e-09, "output_cost_per_token": 0, "litellm_provider": "vertex_ai-embedding-models", "mode": "embedding", @@ -1207,18 +1277,18 @@ "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, + "input_cost_per_token": 6.25e-09, + "input_cost_per_token_batch_requests": 5e-09, "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":{ + "text-multilingual-embedding-preview-0409": { "max_tokens": 3072, "max_input_tokens": 3072, "output_vector_size": 768, - "input_cost_per_token": 0.00000000625, + "input_cost_per_token": 6.25e-09, "output_cost_per_token": 0, "litellm_provider": "vertex_ai-embedding-models", "mode": "embedding", @@ -1228,8 +1298,8 @@ "max_tokens": 4096, "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "palm", "mode": "chat", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -1238,8 +1308,8 @@ "max_tokens": 4096, "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "palm", "mode": "chat", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -1248,8 +1318,8 @@ "max_tokens": 1024, "max_input_tokens": 8192, "max_output_tokens": 1024, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "palm", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -1258,8 +1328,8 @@ "max_tokens": 1024, "max_input_tokens": 8192, "max_output_tokens": 1024, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "palm", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -1268,8 +1338,8 @@ "max_tokens": 1024, "max_input_tokens": 8192, "max_output_tokens": 1024, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "palm", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -1278,8 +1348,8 @@ "max_tokens": 1024, "max_input_tokens": 8192, "max_output_tokens": 1024, - "input_cost_per_token": 0.000000125, - "output_cost_per_token": 0.000000125, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 1.25e-07, "litellm_provider": "palm", "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" @@ -1288,7 +1358,7 @@ "max_tokens": 8192, "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_token": 0.0, + "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "gemini", "mode": "chat", @@ -1299,33 +1369,33 @@ "max_tokens": 8192, "max_input_tokens": 1000000, "max_output_tokens": 8192, - "input_cost_per_token": 0, + "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, + "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, + "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, + "supports_tool_choice": true, "source": "https://ai.google.dev/models/gemini" }, "gemini/gemini-pro-vision": { "max_tokens": 2048, "max_input_tokens": 30720, "max_output_tokens": 2048, - "input_cost_per_token": 0.0, + "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "gemini", "mode": "chat", @@ -1334,238 +1404,489 @@ "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "command-r": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000050, - "output_cost_per_token": 0.0000015, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, "litellm_provider": "cohere_chat", "mode": "chat", "supports_function_calling": true }, "command-light": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.000015, - "output_cost_per_token": 0.000015, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.5e-05, "litellm_provider": "cohere_chat", "mode": "chat" }, "command-r-plus": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, "litellm_provider": "cohere_chat", "mode": "chat", "supports_function_calling": true }, "command-nightly": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.000015, - "output_cost_per_token": 0.000015, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.5e-05, "litellm_provider": "cohere", "mode": "completion" }, - "command": { - "max_tokens": 4096, + "command": { + "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.000015, - "output_cost_per_token": 0.000015, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.5e-05, "litellm_provider": "cohere", "mode": "completion" }, - "command-medium-beta": { - "max_tokens": 4096, + "command-medium-beta": { + "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.000015, - "output_cost_per_token": 0.000015, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.5e-05, "litellm_provider": "cohere", "mode": "completion" }, - "command-xlarge-beta": { - "max_tokens": 4096, + "command-xlarge-beta": { + "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.000015, - "output_cost_per_token": 0.000015, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.5e-05, "litellm_provider": "cohere", "mode": "completion" }, "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000, - "output_cost_per_token": 0.0000, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/openai/gpt-3.5-turbo": { - "max_tokens": 4095, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.000002, - "litellm_provider": "openrouter", + "replicate/meta/llama-2-13b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/openai/gpt-3.5-turbo-16k": { - "max_tokens": 16383, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000004, - "litellm_provider": "openrouter", + "replicate/meta/llama-2-13b-chat": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/openai/gpt-4": { - "max_tokens": 8192, - "input_cost_per_token": 0.00003, - "output_cost_per_token": 0.00006, - "litellm_provider": "openrouter", + "replicate/meta/llama-2-70b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 2.75e-06, + "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/anthropic/claude-instant-v1": { - "max_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.00000163, - "output_cost_per_token": 0.00000551, - "litellm_provider": "openrouter", + "replicate/meta/llama-2-70b-chat": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 2.75e-06, + "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/anthropic/claude-2": { - "max_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.00001102, - "output_cost_per_token": 0.00003268, - "litellm_provider": "openrouter", + "replicate/meta/llama-2-7b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2.5e-07, + "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/google/palm-2-chat-bison": { - "max_tokens": 8000, - "input_cost_per_token": 0.0000005, - "output_cost_per_token": 0.0000005, - "litellm_provider": "openrouter", + "replicate/meta/llama-2-7b-chat": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2.5e-07, + "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/google/palm-2-codechat-bison": { - "max_tokens": 8000, - "input_cost_per_token": 0.0000005, - "output_cost_per_token": 0.0000005, - "litellm_provider": "openrouter", + "replicate/meta/llama-3-70b": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 2.75e-06, + "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/meta-llama/llama-2-13b-chat": { + "replicate/meta/llama-3-70b-instruct": { "max_tokens": 4096, - "input_cost_per_token": 0.0000002, - "output_cost_per_token": 0.0000002, - "litellm_provider": "openrouter", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 2.75e-06, + "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/meta-llama/llama-2-70b-chat": { + "replicate/meta/llama-3-8b": { "max_tokens": 4096, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.0000015, - "litellm_provider": "openrouter", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2.5e-07, + "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/meta-llama/codellama-34b-instruct": { - "max_tokens": 8096, - "input_cost_per_token": 0.0000005, - "output_cost_per_token": 0.0000005, - "litellm_provider": "openrouter", + "replicate/meta/llama-3-8b-instruct": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2.5e-07, + "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/nousresearch/nous-hermes-llama2-13b": { + "replicate/mistralai/mistral-7b-v0.1": { "max_tokens": 4096, - "input_cost_per_token": 0.0000002, - "output_cost_per_token": 0.0000002, - "litellm_provider": "openrouter", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2.5e-07, + "litellm_provider": "replicate", "mode": "chat" }, - "openrouter/mancer/weaver": { - "max_tokens": 8000, - "input_cost_per_token": 0.000005625, - "output_cost_per_token": 0.000005625, + "replicate/mistralai/mistral-7b-instruct-v0.2": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2.5e-07, + "litellm_provider": "replicate", + "mode": "chat" + }, + "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1e-06, + "litellm_provider": "replicate", + "mode": "chat" + }, + "openrouter/microsoft/wizardlm-2-8x22b:nitro": { + "max_tokens": 65536, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 1e-06, "litellm_provider": "openrouter", "mode": "chat" }, - "openrouter/gryphe/mythomax-l2-13b": { + "openrouter/google/gemini-pro-1.5": { "max_tokens": 8192, - "input_cost_per_token": 0.000001875, - "output_cost_per_token": 0.000001875, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 7.5e-06, + "input_cost_per_image": 0.00265, + "litellm_provider": "openrouter", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true + }, + "openrouter/mistralai/mixtral-8x22b-instruct": { + "max_tokens": 65536, + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 6.5e-07, "litellm_provider": "openrouter", "mode": "chat" }, - "openrouter/jondurbin/airoboros-l2-70b-2.1": { - "max_tokens": 4096, - "input_cost_per_token": 0.000013875, - "output_cost_per_token": 0.000013875, + "openrouter/cohere/command-r-plus": { + "max_tokens": 128000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, "litellm_provider": "openrouter", "mode": "chat" }, - "openrouter/undi95/remm-slerp-l2-13b": { - "max_tokens": 6144, - "input_cost_per_token": 0.000001875, - "output_cost_per_token": 0.000001875, + "openrouter/databricks/dbrx-instruct": { + "max_tokens": 32768, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 6e-07, "litellm_provider": "openrouter", "mode": "chat" }, - "openrouter/pygmalionai/mythalion-13b": { - "max_tokens": 4096, - "input_cost_per_token": 0.000001875, - "output_cost_per_token": 0.000001875, + "openrouter/anthropic/claude-3-haiku": { + "max_tokens": 200000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.25e-06, + "input_cost_per_image": 0.0004, + "litellm_provider": "openrouter", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true + }, + "openrouter/anthropic/claude-3-sonnet": { + "max_tokens": 200000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "input_cost_per_image": 0.0048, + "litellm_provider": "openrouter", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true + }, + "openrouter/mistralai/mistral-large": { + "max_tokens": 32000, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "openrouter", "mode": "chat" }, - "openrouter/mistralai/mistral-7b-instruct": { - "max_tokens": 8192, - "input_cost_per_token": 0.00000013, - "output_cost_per_token": 0.00000013, + "openrouter/cognitivecomputations/dolphin-mixtral-8x7b": { + "max_tokens": 32769, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "openrouter", "mode": "chat" }, - "openrouter/mistralai/mistral-7b-instruct:free": { + "openrouter/google/gemini-pro-vision": { + "max_tokens": 45875, + "input_cost_per_token": 1.25e-07, + "output_cost_per_token": 3.75e-07, + "input_cost_per_image": 0.0025, + "litellm_provider": "openrouter", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true + }, + "openrouter/fireworks/firellava-13b": { + "max_tokens": 4096, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/meta-llama/llama-3-8b-instruct:free": { "max_tokens": 8192, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "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, + "openrouter/meta-llama/llama-3-8b-instruct:extended": { + "max_tokens": 16384, + "input_cost_per_token": 2.25e-07, + "output_cost_per_token": 2.25e-06, "litellm_provider": "openrouter", "mode": "chat" }, - "j2-ultra": { + "openrouter/meta-llama/llama-3-70b-instruct:nitro": { "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.000015, - "output_cost_per_token": 0.000015, - "litellm_provider": "ai21", - "mode": "completion" + "input_cost_per_token": 9e-07, + "output_cost_per_token": 9e-07, + "litellm_provider": "openrouter", + "mode": "chat" }, - "j2-mid": { + "openrouter/meta-llama/llama-3-70b-instruct": { "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.00001, - "output_cost_per_token": 0.00001, - "litellm_provider": "ai21", - "mode": "completion" - }, + "input_cost_per_token": 5.9e-07, + "output_cost_per_token": 7.9e-07, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/openai/gpt-4-vision-preview": { + "max_tokens": 130000, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 3e-05, + "input_cost_per_image": 0.01445, + "litellm_provider": "openrouter", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true + }, + "openrouter/openai/gpt-3.5-turbo": { + "max_tokens": 4095, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/openai/gpt-3.5-turbo-16k": { + "max_tokens": 16383, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 4e-06, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/openai/gpt-4": { + "max_tokens": 8192, + "input_cost_per_token": 3e-05, + "output_cost_per_token": 6e-05, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/anthropic/claude-instant-v1": { + "max_tokens": 100000, + "max_output_tokens": 8191, + "input_cost_per_token": 1.63e-06, + "output_cost_per_token": 5.51e-06, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/anthropic/claude-2": { + "max_tokens": 100000, + "max_output_tokens": 8191, + "input_cost_per_token": 1.102e-05, + "output_cost_per_token": 3.268e-05, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/anthropic/claude-3-opus": { + "max_tokens": 4096, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 7.5e-05, + "litellm_provider": "openrouter", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395 + }, + "openrouter/google/palm-2-chat-bison": { + "max_tokens": 25804, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/google/palm-2-codechat-bison": { + "max_tokens": 20070, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/meta-llama/llama-2-13b-chat": { + "max_tokens": 4096, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/meta-llama/llama-2-70b-chat": { + "max_tokens": 4096, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/meta-llama/codellama-34b-instruct": { + "max_tokens": 8096, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/nousresearch/nous-hermes-llama2-13b": { + "max_tokens": 4096, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/mancer/weaver": { + "max_tokens": 8000, + "input_cost_per_token": 5.625e-06, + "output_cost_per_token": 5.625e-06, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/gryphe/mythomax-l2-13b": { + "max_tokens": 8192, + "input_cost_per_token": 1.875e-06, + "output_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/jondurbin/airoboros-l2-70b-2.1": { + "max_tokens": 4096, + "input_cost_per_token": 1.3875e-05, + "output_cost_per_token": 1.3875e-05, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/undi95/remm-slerp-l2-13b": { + "max_tokens": 6144, + "input_cost_per_token": 1.875e-06, + "output_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/pygmalionai/mythalion-13b": { + "max_tokens": 4096, + "input_cost_per_token": 1.875e-06, + "output_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/mistralai/mistral-7b-instruct": { + "max_tokens": 8192, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 1.3e-07, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "openrouter/mistralai/mistral-7b-instruct:free": { + "max_tokens": 8192, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "mode": "chat" + }, + "j2-ultra": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "ai21", + "mode": "completion" + }, + "j2-mid": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 1e-05, + "litellm_provider": "ai21", + "mode": "completion" + }, "j2-light": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000003, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 3e-06, "litellm_provider": "ai21", "mode": "completion" }, @@ -1573,8 +1894,8 @@ "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, - "input_cost_per_token": 0.0000005, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "nlp_cloud", "mode": "completion" }, @@ -1582,104 +1903,113 @@ "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, - "input_cost_per_token": 0.0000005, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "nlp_cloud", "mode": "chat" }, "luminous-base": { - "max_tokens": 2048, - "input_cost_per_token": 0.00003, - "output_cost_per_token": 0.000033, + "max_tokens": 2048, + "input_cost_per_token": 3e-05, + "output_cost_per_token": 3.3e-05, "litellm_provider": "aleph_alpha", "mode": "completion" }, "luminous-base-control": { - "max_tokens": 2048, - "input_cost_per_token": 0.0000375, - "output_cost_per_token": 0.00004125, + "max_tokens": 2048, + "input_cost_per_token": 3.75e-05, + "output_cost_per_token": 4.125e-05, "litellm_provider": "aleph_alpha", "mode": "chat" }, "luminous-extended": { - "max_tokens": 2048, - "input_cost_per_token": 0.000045, - "output_cost_per_token": 0.0000495, + "max_tokens": 2048, + "input_cost_per_token": 4.5e-05, + "output_cost_per_token": 4.95e-05, "litellm_provider": "aleph_alpha", "mode": "completion" }, "luminous-extended-control": { - "max_tokens": 2048, - "input_cost_per_token": 0.00005625, - "output_cost_per_token": 0.000061875, + "max_tokens": 2048, + "input_cost_per_token": 5.625e-05, + "output_cost_per_token": 6.1875e-05, "litellm_provider": "aleph_alpha", "mode": "chat" }, "luminous-supreme": { - "max_tokens": 2048, + "max_tokens": 2048, "input_cost_per_token": 0.000175, "output_cost_per_token": 0.0001925, "litellm_provider": "aleph_alpha", "mode": "completion" }, "luminous-supreme-control": { - "max_tokens": 2048, + "max_tokens": 2048, "input_cost_per_token": 0.00021875, "output_cost_per_token": 0.000240625, "litellm_provider": "aleph_alpha", "mode": "chat" }, "ai21.j2-mid-v1": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "max_output_tokens": 8191, - "input_cost_per_token": 0.0000125, - "output_cost_per_token": 0.0000125, + "max_tokens": 8191, + "max_input_tokens": 8191, + "max_output_tokens": 8191, + "input_cost_per_token": 1.25e-05, + "output_cost_per_token": 1.25e-05, "litellm_provider": "bedrock", "mode": "chat" }, "ai21.j2-ultra-v1": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "max_output_tokens": 8191, - "input_cost_per_token": 0.0000188, - "output_cost_per_token": 0.0000188, + "max_tokens": 8191, + "max_input_tokens": 8191, + "max_output_tokens": 8191, + "input_cost_per_token": 1.88e-05, + "output_cost_per_token": 1.88e-05, "litellm_provider": "bedrock", "mode": "chat" }, "amazon.titan-text-lite-v1": { - "max_tokens": 4000, + "max_tokens": 4000, "max_input_tokens": 42000, - "max_output_tokens": 4000, - "input_cost_per_token": 0.0000003, - "output_cost_per_token": 0.0000004, + "max_output_tokens": 4000, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "bedrock", "mode": "chat" }, "amazon.titan-text-express-v1": { - "max_tokens": 8000, + "max_tokens": 8000, "max_input_tokens": 42000, - "max_output_tokens": 8000, - "input_cost_per_token": 0.0000013, - "output_cost_per_token": 0.0000017, + "max_output_tokens": 8000, + "input_cost_per_token": 1.3e-06, + "output_cost_per_token": 1.7e-06, "litellm_provider": "bedrock", "mode": "chat" }, "amazon.titan-embed-text-v1": { - "max_tokens": 8192, - "max_input_tokens": 8192, + "max_tokens": 8192, + "max_input_tokens": 8192, "output_vector_size": 1536, - "input_cost_per_token": 0.0000001, + "input_cost_per_token": 1e-07, "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", + "litellm_provider": "bedrock", + "mode": "embedding" + }, + "amazon.titan-embed-text-v2:0": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "output_vector_size": 1024, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 0.0, + "litellm_provider": "bedrock", "mode": "embedding" }, "mistral.mistral-7b-instruct-v0:2": { "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000015, - "output_cost_per_token": 0.0000002, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 2e-07, "litellm_provider": "bedrock", "mode": "chat" }, @@ -1687,8 +2017,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000045, - "output_cost_per_token": 0.0000007, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 7e-07, "litellm_provider": "bedrock", "mode": "chat" }, @@ -1696,8 +2026,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, @@ -1705,8 +2035,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000045, - "output_cost_per_token": 0.0000007, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 7e-07, "litellm_provider": "bedrock", "mode": "chat" }, @@ -1714,8 +2044,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000045, - "output_cost_per_token": 0.0000007, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 7e-07, "litellm_provider": "bedrock", "mode": "chat" }, @@ -1723,8 +2053,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000059, - "output_cost_per_token": 0.00000091, + "input_cost_per_token": 5.9e-07, + "output_cost_per_token": 9.1e-07, "litellm_provider": "bedrock", "mode": "chat" }, @@ -1732,8 +2062,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000015, - "output_cost_per_token": 0.0000002, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 2e-07, "litellm_provider": "bedrock", "mode": "chat" }, @@ -1741,8 +2071,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000015, - "output_cost_per_token": 0.0000002, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 2e-07, "litellm_provider": "bedrock", "mode": "chat" }, @@ -1750,8 +2080,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.0000002, - "output_cost_per_token": 0.00000026, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2.6e-07, "litellm_provider": "bedrock", "mode": "chat" }, @@ -1759,8 +2089,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, @@ -1768,8 +2098,8 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, @@ -1777,76 +2107,82 @@ "max_tokens": 8191, "max_input_tokens": 32000, "max_output_tokens": 8191, - "input_cost_per_token": 0.0000104, - "output_cost_per_token": 0.0000312, + "input_cost_per_token": 1.04e-05, + "output_cost_per_token": 3.12e-05, "litellm_provider": "bedrock", "mode": "chat" }, "anthropic.claude-3-sonnet-20240229-v1:0": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 200000, "max_output_tokens": 4096, - "input_cost_per_token": 0.000003, - "output_cost_per_token": 0.000015, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, "litellm_provider": "bedrock", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true }, "anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 200000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.00000125, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.25e-06, "litellm_provider": "bedrock", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true }, "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, + "input_cost_per_token": 1.5e-05, + "output_cost_per_token": 7.5e-05, "litellm_provider": "bedrock", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true }, "anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-east-1/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-west-2/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/ap-northeast-1/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.0455, @@ -1855,7 +2191,7 @@ "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.02527, @@ -1864,224 +2200,224 @@ "mode": "chat" }, "bedrock/eu-central-1/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "max_output_tokens": 8191, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.0415, "output_cost_per_second": 0.0415, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.02305, "output_cost_per_second": 0.02305, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.0175, "output_cost_per_second": 0.0175, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.00972, "output_cost_per_second": 0.00972, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.0175, "output_cost_per_second": 0.0175, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.00972, "output_cost_per_second": 0.00972, "litellm_provider": "bedrock", "mode": "chat" }, "anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "max_output_tokens": 8191, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-east-1/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "max_output_tokens": 8191, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-west-2/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "max_output_tokens": 8191, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/ap-northeast-1/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "max_output_tokens": 8191, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.0455, "output_cost_per_second": 0.0455, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.02527, "output_cost_per_second": 0.02527, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/eu-central-1/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "max_output_tokens": 8191, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.0415, "output_cost_per_second": 0.0415, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.02305, "output_cost_per_second": 0.02305, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.0175, "output_cost_per_second": 0.0175, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.00972, "output_cost_per_second": 0.00972, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.0175, "output_cost_per_second": 0.0175, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2": { - "max_tokens": 8191, + "max_tokens": 8191, "max_input_tokens": 100000, - "max_output_tokens": 8191, + "max_output_tokens": 8191, "input_cost_per_second": 0.00972, "output_cost_per_second": 0.00972, "litellm_provider": "bedrock", "mode": "chat" }, "anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-east-1/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-west-2/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/ap-northeast-1/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.0455, "output_cost_per_second": 0.0455, @@ -2089,8 +2425,8 @@ "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.02527, "output_cost_per_second": 0.02527, @@ -2098,17 +2434,17 @@ "mode": "chat" }, "bedrock/eu-central-1/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.000008, - "output_cost_per_token": 0.000024, + "input_cost_per_token": 8e-06, + "output_cost_per_token": 2.4e-05, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.0415, "output_cost_per_second": 0.0415, @@ -2116,8 +2452,8 @@ "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.02305, "output_cost_per_second": 0.02305, @@ -2125,8 +2461,8 @@ "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.0175, "output_cost_per_second": 0.0175, @@ -2134,8 +2470,8 @@ "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.00972, "output_cost_per_second": 0.00972, @@ -2143,8 +2479,8 @@ "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.0175, "output_cost_per_second": 0.0175, @@ -2152,8 +2488,8 @@ "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.00972, "output_cost_per_second": 0.00972, @@ -2161,26 +2497,26 @@ "mode": "chat" }, "anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000163, - "output_cost_per_token": 0.00000551, + "input_cost_per_token": 1.63e-06, + "output_cost_per_token": 5.51e-06, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-east-1/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.0000008, - "output_cost_per_token": 0.0000024, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.011, "output_cost_per_second": 0.011, @@ -2188,8 +2524,8 @@ "mode": "chat" }, "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.00611, "output_cost_per_second": 0.00611, @@ -2197,8 +2533,8 @@ "mode": "chat" }, "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.011, "output_cost_per_second": 0.011, @@ -2206,8 +2542,8 @@ "mode": "chat" }, "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.00611, "output_cost_per_second": 0.00611, @@ -2215,26 +2551,26 @@ "mode": "chat" }, "bedrock/us-west-2/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.0000008, - "output_cost_per_token": 0.0000024, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 2.4e-06, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000223, - "output_cost_per_token": 0.00000755, + "input_cost_per_token": 2.23e-06, + "output_cost_per_token": 7.55e-06, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.01475, "output_cost_per_second": 0.01475, @@ -2242,8 +2578,8 @@ "mode": "chat" }, "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.008194, "output_cost_per_second": 0.008194, @@ -2251,17 +2587,17 @@ "mode": "chat" }, "bedrock/eu-central-1/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000248, - "output_cost_per_token": 0.00000838, + "input_cost_per_token": 2.48e-06, + "output_cost_per_token": 8.38e-06, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.01635, "output_cost_per_second": 0.01635, @@ -2269,8 +2605,8 @@ "mode": "chat" }, "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, + "max_tokens": 8191, + "max_input_tokens": 100000, "max_output_tokens": 8191, "input_cost_per_second": 0.009083, "output_cost_per_second": 0.009083, @@ -2278,218 +2614,254 @@ "mode": "chat" }, "cohere.command-text-v14": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0000015, - "output_cost_per_token": 0.0000020, + "max_output_tokens": 4096, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 2e-06, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/*/1-month-commitment/cohere.command-text-v14": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 4096, - "max_output_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_second": 0.011, "output_cost_per_second": 0.011, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/*/6-month-commitment/cohere.command-text-v14": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 4096, - "max_output_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_second": 0.0066027, "output_cost_per_second": 0.0066027, "litellm_provider": "bedrock", "mode": "chat" }, "cohere.command-light-text-v14": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0000003, - "output_cost_per_token": 0.0000006, + "max_output_tokens": 4096, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 6e-07, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 4096, - "max_output_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_second": 0.001902, "output_cost_per_second": 0.001902, "litellm_provider": "bedrock", "mode": "chat" }, "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { - "max_tokens": 4096, + "max_tokens": 4096, "max_input_tokens": 4096, - "max_output_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_second": 0.0011416, "output_cost_per_second": 0.0011416, "litellm_provider": "bedrock", "mode": "chat" }, + "cohere.command-r-plus-v1:0": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock", + "mode": "chat" + }, + "cohere.command-r-v1:0": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "bedrock", + "mode": "chat" + }, "cohere.embed-english-v3": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.000000, + "max_tokens": 512, + "max_input_tokens": 512, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, "litellm_provider": "bedrock", "mode": "embedding" }, "cohere.embed-multilingual-v3": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.000000, + "max_tokens": 512, + "max_input_tokens": 512, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, "litellm_provider": "bedrock", "mode": "embedding" }, "meta.llama2-13b-chat-v1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.00000075, - "output_cost_per_token": 0.000001, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 1e-06, "litellm_provider": "bedrock", "mode": "chat" }, "meta.llama2-70b-chat-v1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.00000195, - "output_cost_per_token": 0.00000256, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.95e-06, + "output_cost_per_token": 2.56e-06, + "litellm_provider": "bedrock", + "mode": "chat" + }, + "meta.llama3-8b-instruct-v1:0": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "bedrock", + "mode": "chat" + }, + "meta.llama3-70b-instruct-v1:0": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2.65e-06, + "output_cost_per_token": 3.5e-06, "litellm_provider": "bedrock", "mode": "chat" }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, + "max_tokens": 77, + "max_input_tokens": 77, "output_cost_per_image": 0.018, "litellm_provider": "bedrock", "mode": "image_generation" }, "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, + "max_tokens": 77, + "max_input_tokens": 77, "output_cost_per_image": 0.036, "litellm_provider": "bedrock", "mode": "image_generation" }, "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, + "max_tokens": 77, + "max_input_tokens": 77, "output_cost_per_image": 0.036, "litellm_provider": "bedrock", "mode": "image_generation" }, "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, + "max_tokens": 77, + "max_input_tokens": 77, "output_cost_per_image": 0.072, "litellm_provider": "bedrock", "mode": "image_generation" }, "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { - "max_tokens": 77, - "max_input_tokens": 77, + "max_tokens": 77, + "max_input_tokens": 77, "output_cost_per_image": 0.04, "litellm_provider": "bedrock", "mode": "image_generation" }, "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { - "max_tokens": 77, - "max_input_tokens": 77, + "max_tokens": 77, + "max_input_tokens": 77, "output_cost_per_image": 0.08, "litellm_provider": "bedrock", "mode": "image_generation" }, "sagemaker/meta-textgeneration-llama-2-7b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.000, - "output_cost_per_token": 0.000, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, "litellm_provider": "sagemaker", "mode": "completion" }, "sagemaker/meta-textgeneration-llama-2-7b-f": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.000, - "output_cost_per_token": 0.000, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, "litellm_provider": "sagemaker", "mode": "chat" }, "sagemaker/meta-textgeneration-llama-2-13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.000, - "output_cost_per_token": 0.000, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, "litellm_provider": "sagemaker", "mode": "completion" }, "sagemaker/meta-textgeneration-llama-2-13b-f": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.000, - "output_cost_per_token": 0.000, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, "litellm_provider": "sagemaker", "mode": "chat" }, "sagemaker/meta-textgeneration-llama-2-70b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.000, - "output_cost_per_token": 0.000, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, "litellm_provider": "sagemaker", "mode": "completion" }, "sagemaker/meta-textgeneration-llama-2-70b-b-f": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.000, - "output_cost_per_token": 0.000, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0, + "output_cost_per_token": 0.0, "litellm_provider": "sagemaker", "mode": "chat" }, "together-ai-up-to-3b": { - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.0000001, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1e-07, "litellm_provider": "together_ai" }, "together-ai-3.1b-7b": { - "input_cost_per_token": 0.0000002, - "output_cost_per_token": 0.0000002, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, "litellm_provider": "together_ai" }, "together-ai-7.1b-20b": { "max_tokens": 1000, - "input_cost_per_token": 0.0000004, - "output_cost_per_token": 0.0000004, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "together_ai" }, "together-ai-20.1b-40b": { - "input_cost_per_token": 0.0000008, - "output_cost_per_token": 0.0000008, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 8e-07, "litellm_provider": "together_ai" }, "together-ai-40.1b-70b": { - "input_cost_per_token": 0.0000009, - "output_cost_per_token": 0.0000009, + "input_cost_per_token": 9e-07, + "output_cost_per_token": 9e-07, "litellm_provider": "together_ai" }, "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "input_cost_per_token": 0.0000006, - "output_cost_per_token": 0.0000006, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 6e-07, "litellm_provider": "together_ai", "supports_function_calling": true, "supports_parallel_function_calling": true @@ -2505,36 +2877,36 @@ "supports_parallel_function_calling": true }, "ollama/llama2": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "ollama", "mode": "completion" }, "ollama/llama2:13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "ollama", "mode": "completion" }, "ollama/llama2:70b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "ollama", "mode": "completion" }, "ollama/llama2-uncensored": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, "litellm_provider": "ollama", @@ -2550,8 +2922,8 @@ "mode": "completion" }, "ollama/codellama": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_tokens": 4096, + "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, @@ -2559,8 +2931,8 @@ "mode": "completion" }, "ollama/orca-mini": { - "max_tokens": 4096, - "max_input_tokens": 4096, + "max_tokens": 4096, + "max_input_tokens": 4096, "max_output_tokens": 4096, "input_cost_per_token": 0.0, "output_cost_per_token": 0.0, @@ -2580,8 +2952,8 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000070, - "output_cost_per_token": 0.00000090, + "input_cost_per_token": 7e-07, + "output_cost_per_token": 9e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2589,8 +2961,8 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000022, - "output_cost_per_token": 0.00000022, + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 2.2e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2598,8 +2970,8 @@ "max_tokens": 8191, "max_input_tokens": 32768, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000013, - "output_cost_per_token": 0.00000013, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 1.3e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2607,8 +2979,8 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000070, - "output_cost_per_token": 0.00000090, + "input_cost_per_token": 7e-07, + "output_cost_per_token": 9e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2616,8 +2988,8 @@ "max_tokens": 8191, "max_input_tokens": 32768, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000027, - "output_cost_per_token": 0.00000027, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 2.7e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2625,8 +2997,8 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000060, - "output_cost_per_token": 0.00000060, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2634,8 +3006,8 @@ "max_tokens": 4096, "max_input_tokens": 32000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000027, - "output_cost_per_token": 0.00000027, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 2.7e-07, "litellm_provider": "deepinfra", "mode": "completion" }, @@ -2643,8 +3015,8 @@ "max_tokens": 4096, "max_input_tokens": 16384, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000060, - "output_cost_per_token": 0.00000060, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2652,8 +3024,8 @@ "max_tokens": 8191, "max_input_tokens": 32768, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000027, - "output_cost_per_token": 0.00000027, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 2.7e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2661,8 +3033,8 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000070, - "output_cost_per_token": 0.00000090, + "input_cost_per_token": 7e-07, + "output_cost_per_token": 9e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2670,8 +3042,8 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000060, - "output_cost_per_token": 0.00000060, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2679,8 +3051,8 @@ "max_tokens": 4096, "max_input_tokens": 200000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000013, - "output_cost_per_token": 0.00000013, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 1.3e-07, "litellm_provider": "deepinfra", "mode": "completion" }, @@ -2688,8 +3060,8 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000070, - "output_cost_per_token": 0.00000090, + "input_cost_per_token": 7e-07, + "output_cost_per_token": 9e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2697,8 +3069,8 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000022, - "output_cost_per_token": 0.00000022, + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 2.2e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2706,8 +3078,8 @@ "max_tokens": 8191, "max_input_tokens": 32768, "max_output_tokens": 8191, - "input_cost_per_token": 0.00000020, - "output_cost_per_token": 0.00000020, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2715,8 +3087,8 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000013, - "output_cost_per_token": 0.00000013, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 1.3e-07, "litellm_provider": "deepinfra", "mode": "chat" }, @@ -2724,8 +3096,8 @@ "max_tokens": 4096, "max_input_tokens": 200000, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000060, - "output_cost_per_token": 0.00000060, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "completion" }, @@ -2733,91 +3105,91 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000013, - "output_cost_per_token": 0.00000013, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 1.3e-07, "litellm_provider": "deepinfra", "mode": "chat" }, - "perplexity/codellama-34b-instruct": { + "perplexity/codellama-34b-instruct": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, - "input_cost_per_token": 0.00000035, - "output_cost_per_token": 0.00000140, - "litellm_provider": "perplexity", - "mode": "chat" + "input_cost_per_token": 3.5e-07, + "output_cost_per_token": 1.4e-06, + "litellm_provider": "perplexity", + "mode": "chat" }, - "perplexity/codellama-70b-instruct": { + "perplexity/codellama-70b-instruct": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, - "input_cost_per_token": 0.00000070, - "output_cost_per_token": 0.00000280, - "litellm_provider": "perplexity", - "mode": "chat" + "input_cost_per_token": 7e-07, + "output_cost_per_token": 2.8e-06, + "litellm_provider": "perplexity", + "mode": "chat" }, - "perplexity/pplx-7b-chat": { + "perplexity/pplx-7b-chat": { "max_tokens": 8192, "max_input_tokens": 8192, "max_output_tokens": 8192, - "input_cost_per_token": 0.00000007, - "output_cost_per_token": 0.00000028, - "litellm_provider": "perplexity", - "mode": "chat" + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "perplexity", + "mode": "chat" }, - "perplexity/pplx-70b-chat": { + "perplexity/pplx-70b-chat": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000070, - "output_cost_per_token": 0.00000280, - "litellm_provider": "perplexity", - "mode": "chat" + "input_cost_per_token": 7e-07, + "output_cost_per_token": 2.8e-06, + "litellm_provider": "perplexity", + "mode": "chat" }, - "perplexity/pplx-7b-online": { + "perplexity/pplx-7b-online": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.0000000, - "output_cost_per_token": 0.00000028, + "input_cost_per_token": 0.0, + "output_cost_per_token": 2.8e-07, "input_cost_per_request": 0.005, - "litellm_provider": "perplexity", - "mode": "chat" + "litellm_provider": "perplexity", + "mode": "chat" }, - "perplexity/pplx-70b-online": { + "perplexity/pplx-70b-online": { "max_tokens": 4096, "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0000000, - "output_cost_per_token": 0.00000280, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0, + "output_cost_per_token": 2.8e-06, "input_cost_per_request": 0.005, - "litellm_provider": "perplexity", - "mode": "chat" + "litellm_provider": "perplexity", + "mode": "chat" }, - "perplexity/llama-2-70b-chat": { + "perplexity/llama-2-70b-chat": { "max_tokens": 4096, "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.00000070, - "output_cost_per_token": 0.00000280, - "litellm_provider": "perplexity", - "mode": "chat" + "max_output_tokens": 4096, + "input_cost_per_token": 7e-07, + "output_cost_per_token": 2.8e-06, + "litellm_provider": "perplexity", + "mode": "chat" }, - "perplexity/mistral-7b-instruct": { + "perplexity/mistral-7b-instruct": { "max_tokens": 4096, "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.00000007, - "output_cost_per_token": 0.00000028, - "litellm_provider": "perplexity", - "mode": "chat" + "max_output_tokens": 4096, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "perplexity", + "mode": "chat" }, "perplexity/mixtral-8x7b-instruct": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000007, - "output_cost_per_token": 0.00000028, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, "litellm_provider": "perplexity", "mode": "chat" }, @@ -2825,8 +3197,8 @@ "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, - "input_cost_per_token": 0.00000007, - "output_cost_per_token": 0.00000028, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, "litellm_provider": "perplexity", "mode": "chat" }, @@ -2835,7 +3207,7 @@ "max_input_tokens": 12000, "max_output_tokens": 12000, "input_cost_per_token": 0, - "output_cost_per_token": 0.00000028, + "output_cost_per_token": 2.8e-07, "input_cost_per_request": 0.005, "litellm_provider": "perplexity", "mode": "chat" @@ -2844,8 +3216,8 @@ "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, - "input_cost_per_token": 0.0000006, - "output_cost_per_token": 0.0000018, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 1.8e-06, "litellm_provider": "perplexity", "mode": "chat" }, @@ -2854,167 +3226,166 @@ "max_input_tokens": 12000, "max_output_tokens": 12000, "input_cost_per_token": 0, - "output_cost_per_token": 0.0000018, + "output_cost_per_token": 1.8e-06, "input_cost_per_request": 0.005, "litellm_provider": "perplexity", "mode": "chat" }, - "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { + "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, - "input_cost_per_token": 0.00000015, - "output_cost_per_token": 0.00000015, - "litellm_provider": "anyscale", + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", "mode": "chat", "supports_function_calling": true - }, - "anyscale/Mixtral-8x7B-Instruct-v0.1": { + }, + "anyscale/Mixtral-8x7B-Instruct-v0.1": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, - "input_cost_per_token": 0.00000015, - "output_cost_per_token": 0.00000015, - "litellm_provider": "anyscale", + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", "mode": "chat", "supports_function_calling": true - }, - "anyscale/HuggingFaceH4/zephyr-7b-beta": { + }, + "anyscale/HuggingFaceH4/zephyr-7b-beta": { "max_tokens": 16384, "max_input_tokens": 16384, "max_output_tokens": 16384, - "input_cost_per_token": 0.00000015, - "output_cost_per_token": 0.00000015, - "litellm_provider": "anyscale", + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "mode": "chat" + }, + "anyscale/meta-llama/Llama-2-7b-chat-hf": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", "mode": "chat" - }, - "anyscale/meta-llama/Llama-2-7b-chat-hf": { + }, + "anyscale/meta-llama/Llama-2-13b-chat-hf": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000015, - "output_cost_per_token": 0.00000015, - "litellm_provider": "anyscale", + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2.5e-07, + "litellm_provider": "anyscale", "mode": "chat" - }, - "anyscale/meta-llama/Llama-2-13b-chat-hf": { + }, + "anyscale/meta-llama/Llama-2-70b-chat-hf": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.00000025, - "litellm_provider": "anyscale", + "input_cost_per_token": 1e-06, + "output_cost_per_token": 1e-06, + "litellm_provider": "anyscale", "mode": "chat" - }, - "anyscale/meta-llama/Llama-2-70b-chat-hf": { + }, + "anyscale/codellama/CodeLlama-34b-Instruct-hf": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000001, - "litellm_provider": "anyscale", + "input_cost_per_token": 1e-06, + "output_cost_per_token": 1e-06, + "litellm_provider": "anyscale", "mode": "chat" - }, - "anyscale/codellama/CodeLlama-34b-Instruct-hf": { + }, + "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { + "max_tokens": 3072, + "max_input_tokens": 3072, + "max_output_tokens": 3072, + "input_cost_per_token": 1.923e-06, + "output_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "mode": "chat" + }, + "cloudflare/@cf/meta/llama-2-7b-chat-int8": { + "max_tokens": 2048, + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "input_cost_per_token": 1.923e-06, + "output_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "mode": "chat" + }, + "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 1.923e-06, + "output_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "mode": "chat" + }, + "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 0.000001, - "output_cost_per_token": 0.000001, - "litellm_provider": "anyscale", - "mode": "chat" - }, - "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "max_output_tokens": 3072, - "input_cost_per_token": 0.000001923, - "output_cost_per_token": 0.000001923, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "cloudflare/@cf/meta/llama-2-7b-chat-int8": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "max_output_tokens": 2048, - "input_cost_per_token": 0.000001923, - "output_cost_per_token": 0.000001923, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.000001923, - "output_cost_per_token": 0.000001923, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.000001923, - "output_cost_per_token": 0.000001923, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "voyage/voyage-01": { + "input_cost_per_token": 1.923e-06, + "output_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "mode": "chat" + }, + "voyage/voyage-01": { "max_tokens": 4096, "max_input_tokens": 4096, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, "litellm_provider": "voyage", "mode": "embedding" }, "voyage/voyage-lite-01": { "max_tokens": 4096, "max_input_tokens": 4096, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, "litellm_provider": "voyage", "mode": "embedding" }, "voyage/voyage-large-2": { "max_tokens": 16000, "max_input_tokens": 16000, - "input_cost_per_token": 0.00000012, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 0.0, "litellm_provider": "voyage", "mode": "embedding" }, "voyage/voyage-law-2": { "max_tokens": 16000, "max_input_tokens": 16000, - "input_cost_per_token": 0.00000012, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 0.0, "litellm_provider": "voyage", "mode": "embedding" }, "voyage/voyage-code-2": { "max_tokens": 16000, "max_input_tokens": 16000, - "input_cost_per_token": 0.00000012, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 0.0, "litellm_provider": "voyage", "mode": "embedding" }, "voyage/voyage-2": { "max_tokens": 4000, "max_input_tokens": 4000, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, "litellm_provider": "voyage", "mode": "embedding" }, "voyage/voyage-lite-02-instruct": { "max_tokens": 4000, "max_input_tokens": 4000, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.000000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 0.0, "litellm_provider": "voyage", "mode": "embedding" } - -} +} \ No newline at end of file diff --git a/update_prices.py b/update_prices.py new file mode 100644 index 0000000..76b9ff8 --- /dev/null +++ b/update_prices.py @@ -0,0 +1,73 @@ +import pandas as pd +import tokencost +import json + +# Update model_prices.json with the latest costs from the LiteLLM cost tracker + + +def diff_dicts(dict1, dict2): + diff_keys = dict1.keys() ^ dict2.keys() + differences = {k: (dict1.get(k), dict2.get(k)) for k in diff_keys} + differences.update({k: (dict1[k], dict2[k]) for k in dict1 if k in dict2 and dict1[k] != dict2[k]}) + + if differences: + print("Differences found:") + for key, (val1, val2) in differences.items(): + print(f"{key}: {val1} != {val2}") + else: + print("No differences found.") + + if differences: + return True + else: + return False + + +with open('tokencost/model_prices.json', 'r') as f: + model_prices = json.load(f) + +if diff_dicts(model_prices, tokencost.TOKEN_COSTS): + print('Updating model_prices.json') + with open('tokencost/model_prices.json', 'w') as f: + json.dump(tokencost.TOKEN_COSTS, f, indent=4) +# Load the data +df = pd.DataFrame(tokencost.TOKEN_COSTS).T +df['max_input_tokens'] = df['max_input_tokens'].apply(lambda x: '{:,.0f}'.format(x)) +df['max_tokens'] = df['max_tokens'].apply(lambda x: '{:,.0f}'.format(x)) + + +# Updated function to format the cost or handle NaN + + +def format_cost(x): + if pd.isna(x): + return '--' + else: + # Ensure the number is treated as a float and format it + return '${:.8f}'.format(float(x)) + + +# Apply the formatting function +# Apply the formatting function using DataFrame.apply and lambda +df[['input_cost_per_token', 'output_cost_per_token']] = df[[ + 'input_cost_per_token', 'output_cost_per_token']].apply(lambda x: x.map(format_cost)) + + +column_mapping = { + 'input_cost_per_token': 'Prompt Cost (USD)', + 'output_cost_per_token': 'Completion Cost (USD)', + 'max_input_tokens': 'Max Prompt Tokens', + 'max_output_tokens': 'Max Output Tokens', + 'model_name': 'Model Name' +} + +# Assuming the keys of the JSON data represent the model names and have been set as the index +df['Model Name'] = df.index + +# Apply the column renaming +df.rename(columns=column_mapping, inplace=True) + +# Write the DataFrame with the correct column names as markdown to a file +with open('pricing_table.md', 'w') as f: + f.write(df[['Model Name', 'Prompt Cost (USD)', 'Completion Cost (USD)', + 'Max Prompt Tokens', 'Max Output Tokens']].to_markdown(index=False))