Helicone

What you can use it for

Track model requests and API costs in a self-hosted proxy.

• Replace the gateway request-observability and per-request cost-monitoring slice using the Apache-2.0 self-hosted Helicone core. Not complete LLM Gateway routing, credits or provider-payment parity.

Before you switch

This comparison covers request logging and cost visibility, not every routing or billing feature. The historical user report predates the newer Rust AI Gateway and does not prove that separate product. Self-hosting requires databases, upgrades and storage; model providers still charge.

Alternatives to these paid apps

Each comparison covers the workflow described above, rather than every paid feature.

LLM Gateway→Website ↗