Open-source LLM observability platform and smart proxy for monitoring costs, latency, and intelligent caching with one line of code.
Cloud free tier includes one hundred thousand requests per month; open-source core supports full self-hosting via Docker.
Helicone is the open-source LLM observability platform and developer-first proxy. Integrating with a simple base URL change, it delivers real-time visibility into model spending, token metrics, latency breakdowns, intelligent edge caching, and user rate limiting without altering code logic.