diff --git a/embedchain/embedchain/config/llm/base.py b/embedchain/embedchain/config/llm/base.py index 284deebacd..1e041ea589 100644 --- a/embedchain/embedchain/config/llm/base.py +++ b/embedchain/embedchain/config/llm/base.py @@ -234,7 +234,7 @@ def __init__( self.api_version = api_version if token_usage: - f = open("model_prices_and_context_window.json") + f = open("config/model_prices_and_context_window.json") self.model_pricing_map = json.load(f) if isinstance(prompt, str): diff --git a/embedchain/embedchain/config/model_prices_and_context_window.json b/embedchain/embedchain/config/model_prices_and_context_window.json new file mode 100644 index 0000000000..1a9b6e4d01 --- /dev/null +++ b/embedchain/embedchain/config/model_prices_and_context_window.json @@ -0,0 +1,803 @@ +{ + "openai/gpt-4": { + "max_tokens": 4096, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00003, + "output_cost_per_token": 0.00006 + }, + "openai/gpt-4o": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000005, + "output_cost_per_token": 0.000015 + }, + "openai/gpt-4o-2024-05-13": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000005, + "output_cost_per_token": 0.000015 + }, + "openai/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 + }, + "openai/gpt-4-0314": { + "max_tokens": 4096, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00003, + "output_cost_per_token": 0.00006 + }, + "openai/gpt-4-0613": { + "max_tokens": 4096, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00003, + "output_cost_per_token": 0.00006 + }, + "openai/gpt-4-32k": { + "max_tokens": 4096, + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00006, + "output_cost_per_token": 0.00012 + }, + "openai/gpt-4-32k-0314": { + "max_tokens": 4096, + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00006, + "output_cost_per_token": 0.00012 + }, + "openai/gpt-4-32k-0613": { + "max_tokens": 4096, + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00006, + "output_cost_per_token": 0.00012 + }, + "openai/gpt-4-turbo": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00003 + }, + "openai/gpt-4-turbo-2024-04-09": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00003 + }, + "openai/gpt-4-1106-preview": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00003 + }, + "openai/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 + }, + "openai/gpt-3.5-turbo": { + "max_tokens": 4097, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000002 + }, + "openai/gpt-3.5-turbo-0301": { + "max_tokens": 4097, + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000002 + }, + "openai/gpt-3.5-turbo-0613": { + "input_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000002 + }, + "openai/gpt-3.5-turbo-1106": { + "max_tokens": 16385, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0000010, + "output_cost_per_token": 0.0000020 + }, + "openai/gpt-3.5-turbo-0125": { + "max_tokens": 16385, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0000005, + "output_cost_per_token": 0.0000015 + }, + "openai/gpt-3.5-turbo-16k": { + "max_tokens": 16385, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000004 + }, + "openai/gpt-3.5-turbo-16k-0613": { + "max_tokens": 16385, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000004 + }, + "openai/text-embedding-3-large": { + "max_tokens": 8191, + "max_input_tokens": 8191, + "output_vector_size": 3072, + "input_cost_per_token": 0.00000013, + "output_cost_per_token": 0.000000 + }, + "openai/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 + }, + "openai/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 + }, + "openai/text-embedding-ada-002-v2": { + "max_tokens": 8191, + "max_input_tokens": 8191, + "input_cost_per_token": 0.0000001, + "output_cost_per_token": 0.000000 + }, + "openai/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 + }, + "openai/davinci-002": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000002 + }, + "openai/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 + }, + "openai/gpt-3.5-turbo-instruct-0914": { + "max_tokens": 4097, + "max_input_tokens": 8192, + "max_output_tokens": 4097, + "input_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000002 + }, + "azure/gpt-4o": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000005, + "output_cost_per_token": 0.000015 + }, + "azure/gpt-4-turbo-2024-04-09": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00003 + }, + "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 + }, + "azure/gpt-4-1106-preview": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00003 + }, + "azure/gpt-4-0613": { + "max_tokens": 4096, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00003, + "output_cost_per_token": 0.00006 + }, + "azure/gpt-4-32k-0613": { + "max_tokens": 4096, + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00006, + "output_cost_per_token": 0.00012 + }, + "azure/gpt-4-32k": { + "max_tokens": 4096, + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00006, + "output_cost_per_token": 0.00012 + }, + "azure/gpt-4": { + "max_tokens": 4096, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00003, + "output_cost_per_token": 0.00006 + }, + "azure/gpt-4-turbo": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00003 + }, + "azure/gpt-4-turbo-vision-preview": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00003 + }, + "azure/gpt-3.5-turbo-16k-0613": { + "max_tokens": 4096, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000004 + }, + "azure/gpt-3.5-turbo-1106": { + "max_tokens": 4096, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000002 + }, + "azure/gpt-3.5-turbo-0125": { + "max_tokens": 4096, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0000005, + "output_cost_per_token": 0.0000015 + }, + "azure/gpt-3.5-turbo-16k": { + "max_tokens": 4096, + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000004 + }, + "azure/gpt-3.5-turbo": { + "max_tokens": 4096, + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0000005, + "output_cost_per_token": 0.0000015 + }, + "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 + }, + "azure/gpt-3.5-turbo-instruct": { + "max_tokens": 4097, + "max_input_tokens": 4097, + "input_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000002 + }, + "azure/text-embedding-ada-002": { + "max_tokens": 8191, + "max_input_tokens": 8191, + "input_cost_per_token": 0.0000001, + "output_cost_per_token": 0.000000 + }, + "azure/text-embedding-3-large": { + "max_tokens": 8191, + "max_input_tokens": 8191, + "input_cost_per_token": 0.00000013, + "output_cost_per_token": 0.000000 + }, + "azure/text-embedding-3-small": { + "max_tokens": 8191, + "max_input_tokens": 8191, + "input_cost_per_token": 0.00000002, + "output_cost_per_token": 0.000000 + }, + "mistralai/mistral-tiny": { + "max_tokens": 8191, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.00000025, + "output_cost_per_token": 0.00000025 + }, + "mistralai/mistral-small": { + "max_tokens": 8191, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000003 + }, + "mistralai/mistral-small-latest": { + "max_tokens": 8191, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000003 + }, + "mistralai/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 + }, + "mistralai/mistral-medium-latest": { + "max_tokens": 8191, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.0000027, + "output_cost_per_token": 0.0000081 + }, + "mistralai/mistral-medium-2312": { + "max_tokens": 8191, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.0000027, + "output_cost_per_token": 0.0000081 + }, + "mistralai/mistral-large-latest": { + "max_tokens": 8191, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.000004, + "output_cost_per_token": 0.000012 + }, + "mistralai/mistral-large-2402": { + "max_tokens": 8191, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.000004, + "output_cost_per_token": 0.000012 + }, + "mistralai/open-mistral-7b": { + "max_tokens": 8191, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.00000025, + "output_cost_per_token": 0.00000025 + }, + "mistralai/open-mixtral-8x7b": { + "max_tokens": 8191, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.0000007, + "output_cost_per_token": 0.0000007 + }, + "mistralai/open-mixtral-8x22b": { + "max_tokens": 8191, + "max_input_tokens": 64000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000006 + }, + "mistralai/codestral-latest": { + "max_tokens": 8191, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000003 + }, + "mistralai/codestral-2405": { + "max_tokens": 8191, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000003 + }, + "mistralai/mistral-embed": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "input_cost_per_token": 0.0000001, + "output_cost_per_token": 0.0 + }, + "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 + }, + "groq/llama3-8b-8192": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000010, + "output_cost_per_token": 0.00000010 + }, + "groq/llama3-70b-8192": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000064, + "output_cost_per_token": 0.00000080 + }, + "groq/mixtral-8x7b-32768": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 0.00000027, + "output_cost_per_token": 0.00000027 + }, + "groq/gemma-7b-it": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000010, + "output_cost_per_token": 0.00000010 + }, + "anthropic/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 + }, + "anthropic/claude-instant-1.2": { + "max_tokens": 8191, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.000000163, + "output_cost_per_token": 0.000000551 + }, + "anthropic/claude-2": { + "max_tokens": 8191, + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.000008, + "output_cost_per_token": 0.000024 + }, + "anthropic/claude-2.1": { + "max_tokens": 8191, + "max_input_tokens": 200000, + "max_output_tokens": 8191, + "input_cost_per_token": 0.000008, + "output_cost_per_token": 0.000024 + }, + "anthropic/claude-3-haiku-20240307": { + "max_tokens": 4096, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00000025, + "output_cost_per_token": 0.00000125 + }, + "anthropic/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 + }, + "anthropic/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 + }, + "vertexai/chat-bison": { + "max_tokens": 4096, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/chat-bison@001": { + "max_tokens": 4096, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/chat-bison@002": { + "max_tokens": 4096, + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/chat-bison-32k": { + "max_tokens": 8192, + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/code-bison": { + "max_tokens": 1024, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/code-bison@001": { + "max_tokens": 1024, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/code-gecko@001": { + "max_tokens": 64, + "max_input_tokens": 2048, + "max_output_tokens": 64, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/code-gecko@002": { + "max_tokens": 64, + "max_input_tokens": 2048, + "max_output_tokens": 64, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/code-gecko": { + "max_tokens": 64, + "max_input_tokens": 2048, + "max_output_tokens": 64, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/codechat-bison": { + "max_tokens": 1024, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/codechat-bison@001": { + "max_tokens": 1024, + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/codechat-bison-32k": { + "max_tokens": 8192, + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.000000125 + }, + "vertexai/gemini-pro": { + "max_tokens": 8192, + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "input_cost_per_token": 0.00000025, + "output_cost_per_token": 0.0000005 + }, + "vertexai/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 + }, + "vertexai/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 + }, + "vertexai/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 + }, + "vertexai/gemini-1.5-pro": { + "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "input_cost_per_token": 0.000000625, + "output_cost_per_token": 0.000001875 + }, + "vertexai/gemini-1.5-flash-001": { + "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "input_cost_per_token": 0, + "output_cost_per_token": 0 + }, + "vertexai/gemini-1.5-flash-preview-0514": { + "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "input_cost_per_token": 0, + "output_cost_per_token": 0 + }, + "vertexai/gemini-1.5-pro-001": { + "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "input_cost_per_token": 0.000000625, + "output_cost_per_token": 0.000001875 + }, + "vertexai/gemini-1.5-pro-preview-0514": { + "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "input_cost_per_token": 0.000000625, + "output_cost_per_token": 0.000001875 + }, + "vertexai/gemini-1.5-pro-preview-0215": { + "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "input_cost_per_token": 0.000000625, + "output_cost_per_token": 0.000001875 + }, + "vertexai/gemini-1.5-pro-preview-0409": { + "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "input_cost_per_token": 0.000000625, + "output_cost_per_token": 0.000001875 + }, + "vertexai/gemini-experimental": { + "max_tokens": 8192, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "input_cost_per_token": 0, + "output_cost_per_token": 0 + }, + "vertexai/gemini-pro-vision": { + "max_tokens": 2048, + "max_input_tokens": 16384, + "max_output_tokens": 2048, + "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 + }, + "vertexai/gemini-1.0-pro-vision": { + "max_tokens": 2048, + "max_input_tokens": 16384, + "max_output_tokens": 2048, + "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 + }, + "vertexai/gemini-1.0-pro-vision-001": { + "max_tokens": 2048, + "max_input_tokens": 16384, + "max_output_tokens": 2048, + "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 + }, + "vertexai/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 + }, + "vertexai/claude-3-haiku@20240307": { + "max_tokens": 4096, + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00000025, + "output_cost_per_token": 0.00000125 + }, + "vertexai/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 + }, + "cohere/command-r": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00000050, + "output_cost_per_token": 0.0000015 + }, + "cohere/command-light": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000015, + "output_cost_per_token": 0.000015 + }, + "cohere/command-r-plus": { + "max_tokens": 4096, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015 + }, + "cohere/command-nightly": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000015, + "output_cost_per_token": 0.000015 + }, + "cohere/command": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 0.000015, + "output_cost_per_token": 0.000015 + }, + "cohere/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 + }, + "cohere/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 + }, + "together/together-ai-up-to-3b": { + "input_cost_per_token": 0.0000001, + "output_cost_per_token": 0.0000001 + }, + "together/together-ai-3.1b-7b": { + "input_cost_per_token": 0.0000002, + "output_cost_per_token": 0.0000002 + }, + "together/together-ai-7.1b-20b": { + "max_tokens": 1000, + "input_cost_per_token": 0.0000004, + "output_cost_per_token": 0.0000004 + }, + "together/together-ai-20.1b-40b": { + "input_cost_per_token": 0.0000008, + "output_cost_per_token": 0.0000008 + }, + "together/together-ai-40.1b-70b": { + "input_cost_per_token": 0.0000009, + "output_cost_per_token": 0.0000009 + }, + "together/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 0.0000006, + "output_cost_per_token": 0.0000006 + } +} \ No newline at end of file