Provider pricing

Helicone AI API pricing

Helicone is the open-source observability layer for LLM apps — drop-in proxy gateway that logs every request, caches identical prompts, runs offline evals, and provides per-user/per-feature cost dashboards. Supports OpenAI, Anthropic, Google, OpenRouter, Together, and any OpenAI-compatible provider.

Founded2023
HeadquartersSan Francisco, CA
Tracked modelsDirectory

Best for

Engineering teams that need production-grade LLM observability without DIY infrastructure.

Strengths

  • One-line gateway proxy for full request/response logging
  • Free tier covers 100k requests/month with full retention
  • Built-in caching, retries, and rate limiting
  • Open source — self-host or use the managed cloud