Helicone
Gateway and observability in one proxy — Apache-2.0, now in maintenance under Mintlify.
Helicone is an open-source AI gateway and observability platform with logging, caching and cost tracking built into the proxy rather than added alongside it — the practical difference from LiteLLM, where observability is thin and usually paired with something else. The platform (Helicone/helicone) is Apache-2.0 and self-hostable as a set of containers; a separate Rust gateway (Helicone/ai-gateway) is GPL-3.0. Helicone joined Mintlify in March 2026 and is now maintained rather than developed: fixes continue, new features do not. Fine for a stable setup today; weigh it against actively developed options before building on it for years.
What it does well
- +The platform is Apache-2.0 and fully self-hostable
- +Routing and observability in one component — less to assemble
- +Proxy-based: nothing to instrument in your code to start
- +Hosted option if you would rather not run it
Where it falls short
- −Maintenance mode since the Mintlify acquisition (March 2026) — no new development
- −The separate Rust gateway is GPL-3.0, not Apache-2.0
- −Fewer providers supported than LiteLLM's 100+
- −The hosted tier means prompts transit a third party — the thing self-hosting avoided
Helicone as an alternative to
Where Helicone shows up in our comparisons, and how it ranked.
Helicone head-to-head
Straight comparisons against the tools people weigh it against.