Logging LLM Inferences
Supported Models
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 ID | Model Name |
---|---|
gpt-4 | GPT-4 |
gpt-4o | GPT-4-O |
gpt-4o-mini | GPT-4-O-Mini |
gpt-4-0613 | GPT-4-0613 |
gpt-4-32k | GPT-4-32K |
gpt-4-32k-0613 | GPT-4-32K-0613 |
gpt-4-turbo | GPT-4-Turbo |
gpt-4-turbo-preview | GPT-4-Turbo-Preview |
gpt-4-0125-preview | GPT-4-0125-Preview |
gpt-4-1106-preview | GPT-4-1106-Preview |
gpt-3.5-turbo | GPT-3.5-Turbo |
gpt-3.5-turbo-0613 | GPT-3.5-Turbo-0613 |
gpt-3.5-turbo-16k | GPT-3.5-Turbo-16K |
gpt-3.5-turbo-16k-0613 | GPT-3.5-Turbo-16K-0613 |
gpt-3.5-turbo-1106 | GPT-3.5-Turbo-1106 |
gpt-3.5-turbo-0125 | GPT-3.5-Turbo-0125 |
text-davinci-003 | Text-Davinci-003 |
text-davinci-002 | Text-Davinci-002 |
text-davinci-001 | Text-Davinci-001 |
text-curie-001 | Text-Curie-001 |
text-babbage-001 | Text-Babbage-001 |
text-ada-001 | Text-Ada-001 |
command-light | Command-Light |
command | Command |
command-r | Command-R |
command-r-plus | Command-R-Plus |
gemini/gemini-prod | Gemini-Prod |
gemini/gemini-pro | Gemini-Pro |
gemini/gemini-1.5-pro-latest | Gemini-1.5-Pro-Latest |
claude-2 | Claude-2 |
claude-2.1 | Claude-2.1 |
claude-3-haiku-20240307 | Claude-3-Haiku-20240307 |
claude-3-sonnet-20240229 | Claude-3-Sonnet-20240229 |
claude-3-opus-20240229 | Claude-3-Opus-20240229 |
mistral/mistral-tiny | Mistral-Tiny |
mistral/mistral-small | Mistral-Small |
mistral/mistral-medium | Mistral-Medium |
mistral/mistral-large-latest | Mistral-Large-Latest |
mistral/mistral-large-2407 | Mistral-Large-2407 |
mistral/open-mistral-nemo-2407 | Mistral-Nemo-2407 |
generic | Generic |
groq/llama3-8b-8192 | GROQ-Llama3-8B-8192 |
groq/llama3-70b-8192 | GROQ-Llama3-70B-8192 |
groq/llama-3.1-405b-reasoning | GROQ-Llama-3.1-405B-Reasoning |
groq/llama-3.1-70b-versatile | GROQ-Llama-3.1-70B-Versatile |
groq/llama-3.1-8b-instant | GROQ-Llama-3.1-8B-Instant |
huggingface/meta-llama/meta-llama-3-8b | Huggingface-Meta-Llama-3-8B |
huggingface/meta-llama/meta-llama-3-70b | Huggingface-Meta-Llama-3-70B |
perplexity/mistral-7b-instruct | Perplexity-Mistral-7B-Instruct |
perplexity/llama-3-sonar-small-32k-chat | Perplexity-Llama-3-Sonar-Small-32K-Chat |
perplexity/llama-3-sonar-large-32k-chat | Perplexity-Llama-3-Sonar-Large-32K-Chat |
perplexity/llama-3-8b-instruct | Perplexity-Llama-3-8B-Instruct |
perplexity/llama-3-70b-instruct | Perplexity-Llama-3-70B-Instruct |
perplexity/mixtral-8x7b-instruct | Perplexity-Mixtral-8X7B-Instruct |
perplexity/llama-3-sonar-small-32k-online | Perplexity-Llama-3-Sonar-Small-32K-Online |
perplexity/llama-3-sonar-large-32k-online | Perplexity-Llama-3-Sonar-Large-32K-Online |
perplexity/llama-3.1-sonar-small-128k-online | Perplexity-Llama-3.1-Sonar-Small-128K-Online |
perplexity/llama-3.1-sonar-small-128k-chat | Perplexity-Llama-3.1-Sonar-Small-128K-Chat |
perplexity/llama-3.1-sonar-large-128k-online | Perplexity-Llama-3.1-Sonar-Large-128K-Online |
perplexity/llama-3.1-sonar-large-128k-chat | Perplexity-Llama-3.1-Sonar-Large-128K-Chat |
perplexity/llama-3.1-8b-instruct | Perplexity-Llama-3.1-8B-Instruct |
perplexity/llama-3.1-70b-instruct | Perplexity-Llama-3.1-70B-Instruct |
claude-3-5-sonnet-20240620 | Claude-3.5-Sonnet-20240620 |
gpt-4o-2024-05-13 | GPT-4-O-2024-05-13 |