Athina logging is LLM agnostic.This means you can log prompts and responses from any LLM model.Simply change the language_model_id field to whatever model you are using.language_model_id is just a string field that you can use to identify the model you are using.You can log any string identifier here.
For the models below, Athina will also automatically extract the token usage and cost from the language_model_id field. This is done using LiteLLM.
Model IDModel Name
gpt-4GPT-4
gpt-4oGPT-4-O
gpt-4o-miniGPT-4-O-Mini
gpt-4-0613GPT-4-0613
gpt-4-32kGPT-4-32K
gpt-4-32k-0613GPT-4-32K-0613
gpt-4-turboGPT-4-Turbo
gpt-4-turbo-previewGPT-4-Turbo-Preview
gpt-4-0125-previewGPT-4-0125-Preview
gpt-4-1106-previewGPT-4-1106-Preview
gpt-3.5-turboGPT-3.5-Turbo
gpt-3.5-turbo-0613GPT-3.5-Turbo-0613
gpt-3.5-turbo-16kGPT-3.5-Turbo-16K
gpt-3.5-turbo-16k-0613GPT-3.5-Turbo-16K-0613
gpt-3.5-turbo-1106GPT-3.5-Turbo-1106
gpt-3.5-turbo-0125GPT-3.5-Turbo-0125
text-davinci-003Text-Davinci-003
text-davinci-002Text-Davinci-002
text-davinci-001Text-Davinci-001
text-curie-001Text-Curie-001
text-babbage-001Text-Babbage-001
text-ada-001Text-Ada-001
command-lightCommand-Light
commandCommand
command-rCommand-R
command-r-plusCommand-R-Plus
gemini/gemini-prodGemini-Prod
gemini/gemini-proGemini-Pro
gemini/gemini-1.5-pro-latestGemini-1.5-Pro-Latest
claude-2Claude-2
claude-2.1Claude-2.1
claude-3-haiku-20240307Claude-3-Haiku-20240307
claude-3-sonnet-20240229Claude-3-Sonnet-20240229
claude-3-opus-20240229Claude-3-Opus-20240229
mistral/mistral-tinyMistral-Tiny
mistral/mistral-smallMistral-Small
mistral/mistral-mediumMistral-Medium
mistral/mistral-large-latestMistral-Large-Latest
mistral/mistral-large-2407Mistral-Large-2407
mistral/open-mistral-nemo-2407Mistral-Nemo-2407
genericGeneric
groq/llama3-8b-8192GROQ-Llama3-8B-8192
groq/llama3-70b-8192GROQ-Llama3-70B-8192
groq/llama-3.1-405b-reasoningGROQ-Llama-3.1-405B-Reasoning
groq/llama-3.1-70b-versatileGROQ-Llama-3.1-70B-Versatile
groq/llama-3.1-8b-instantGROQ-Llama-3.1-8B-Instant
huggingface/meta-llama/meta-llama-3-8bHuggingface-Meta-Llama-3-8B
huggingface/meta-llama/meta-llama-3-70bHuggingface-Meta-Llama-3-70B
perplexity/mistral-7b-instructPerplexity-Mistral-7B-Instruct
perplexity/llama-3-sonar-small-32k-chatPerplexity-Llama-3-Sonar-Small-32K-Chat
perplexity/llama-3-sonar-large-32k-chatPerplexity-Llama-3-Sonar-Large-32K-Chat
perplexity/llama-3-8b-instructPerplexity-Llama-3-8B-Instruct
perplexity/llama-3-70b-instructPerplexity-Llama-3-70B-Instruct
perplexity/mixtral-8x7b-instructPerplexity-Mixtral-8X7B-Instruct
perplexity/llama-3-sonar-small-32k-onlinePerplexity-Llama-3-Sonar-Small-32K-Online
perplexity/llama-3-sonar-large-32k-onlinePerplexity-Llama-3-Sonar-Large-32K-Online
perplexity/llama-3.1-sonar-small-128k-onlinePerplexity-Llama-3.1-Sonar-Small-128K-Online
perplexity/llama-3.1-sonar-small-128k-chatPerplexity-Llama-3.1-Sonar-Small-128K-Chat
perplexity/llama-3.1-sonar-large-128k-onlinePerplexity-Llama-3.1-Sonar-Large-128K-Online
perplexity/llama-3.1-sonar-large-128k-chatPerplexity-Llama-3.1-Sonar-Large-128K-Chat
perplexity/llama-3.1-8b-instructPerplexity-Llama-3.1-8B-Instruct
perplexity/llama-3.1-70b-instructPerplexity-Llama-3.1-70B-Instruct
claude-3-5-sonnet-20240620Claude-3.5-Sonnet-20240620
gpt-4o-2024-05-13GPT-4-O-2024-05-13