Helicone AI
Open-source LLM observability platform and AI gateway for logging, monitoring, and analyzing every request your AI app makes.
About
Helicone is an observability and routing layer that sits between your application and language model providers like OpenAI, Anthropic, Azure, and Together AI. Every LLM call is logged with full request and response data, latency metrics, token counts, and cost so you can debug issues and track spending without building custom instrumentation. The platform includes prompt versioning, dataset management, a playground for testing changes, and session tracking for multi-turn agent interactions. It is backed by Y Combinator and used by AI development teams across multiple industries. The Hobby plan is free up to 10,000 requests per month, with paid plans starting at $79 per month.