​

Helicone Observability

Helicone is a streamlined tool that seamlessly integrates into any existing codebase, regardless of the programming language. This is achieved by providing a new base URL endpoint that proxies the traffic to TogetherAI.

Helicone offers a range of features, primarily used for:

• Data Ingestion and normalization with other LLM providers
• Prompt application analytics and insights
• Caching to economize on requests

For more information, visit Helicone’s documentation or contact us.

​

Getting Started

​

1. Create a Helicone Account

Start by creating a Helicone account and obtaining your API key from the Helicone Dashboard.

​

2. Implement Helicone

Wherever you use the TogetherAI API, simply substitute the base URL with https://together.helicone.ai and include the Helicone-Auth header with your Helicone API key.

TOGETHER_API_KEY = os.environ.get("TOGETHER_API_KEY")
HELICONE_API_KEY = os.environ.get("HELICONE_API_KEY")

client = OpenAI(
  api_key=TOGETHER_API_KEY,
  # base_url='https://api.together.xyz/v1', Old
  base_url='https://together.helicone.ai/v1', # Change to Helicone
  default_headers={
    "Helicone-Auth": f"Bearer {HELICONE_API_KEY}", # Add Helicone API Key
  }
)

​

3. Start Utilizing Helicone

Congratulations! You are now using Helicone to proxy your requests to TogetherAI. You can now leverage Helicone’s features such as data ingestion, caching, and analytics.