Helicone integration

Helicone is an open source observability platform that proxies your LLM requests and provides key insights into your usage, spend, latency and more.

To reference prompts in Helicone:

1. Log into Helicone or create an account. Once you have an account, you can generate an API key.

2. Set HELICONE_API_KEY in your shell, in a file passed with --env-file, or in your config's top-level env block.

3. Use the helicone:// prefix for your prompts, followed by the Helicone prompt id and version. For example:

   prompts:
     - 'helicone://my-cool-prompt:5.2'
   
   providers:
     - openai:gpt-5-mini
   
   tests:
     - vars:
         # ...

Variables from your promptfoo test cases will be automatically plugged into the Helicone prompt as variables.

You can follow this guide to create a Prompt using Helicone