LiteLLM is a model I/O library to standardize API calls to Azure, Anthropic, OpenAI, etc. Here’s how you can log your LLM API calls to Helicone from LiteLLM.

Approach 1: Use Callbacks

1 line integration

Add HELICONE_API_KEY to your environment variables.

export HELICONE_API_KEY=sk-<your-api-key>
# You can also set it in your code (See below)

Tell LiteLLM you want to log your data to Helicone


Complete code

from litellm import completion

## set env variables
os.environ["HELICONE_API_KEY"] = "your-helicone-key" 
os.environ["OPENAI_API_KEY"], os.environ["COHERE_API_KEY"] = "", ""

# set callbacks

#openai call
response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hi πŸ‘‹ - i'm openai"}]) 

#cohere call
response = completion(model="command-nightly", messages=[{"role": "user", "content": "Hi πŸ‘‹ - i'm cohere"}]) 

Approach 2: [OpenAI + Azure only] Use Helicone as a proxy

Helicone provides advanced functionality like caching, etc. which they support for Azure and OpenAI.

If you want to use Helicone to proxy your OpenAI/Azure requests, then you can -

2 line integration

litellm.api_url = """" # set the base url
litellm.headers = {"Helicone-Auth": f"Bearer {os.getenv('HELICONE_API_KEY')}"} # set your headers

Complete code

import litellm
from litellm import completion

litellm.api_base = ""
litellm.headers = {"Helicone-Auth": f"Bearer {os.getenv('HELICONE_API_KEY')}"}

response = litellm.completion(
    messages=[{"role": "user", "content": "how does a court case get to the Supreme Court?"}]


Feel free to check it out and tell us what you think πŸ‘‹