MerchantryTidbits

llm-inference / api

Helicone

Capability: Helicone

Use it when

  • proxy OpenAI calls for cost and latency observability
  • trace LLM requests without changing app logic much

What it solves

cost-per-call-too-high

Install

npm i @helicone/helicone

Invoke

# see https://github.com/Helicone/helicone
npm i @helicone/helicone

Alternatives

No reviewed alternatives recorded yet.