I m launching Frugal Relay tomorrow and would value feedback from developers and technical creators.
The problem I m trying to solve is simple: many teams want to use GPT and Claude models, but official API pricing, provider-specific integrations, and separate billing setups make experimentation and production costs harder to manage.
Frugal Relay takes the OpenAI-compatible gateway approach: one API for GPT and Claude models, with minimal client-side configuration changes.
Before launch, I d love to understand:
The 10x cost reduction is wild if the latency holds up in real apps. One thing that would seal the deal for me is per-route spend caps, like set a monthly ceiling per API key and get an email or webhook when you hit 80 percent. Right now it sounds like you have the analytics but not the guardrails to actually prevent a runaway script from burning through the budget overnight.
@berivan225074 We do support that today: set a monthly spend cap per API key, get email or webhook alerts at thresholds such as 80%, and enforce a hard stop at the cap. The goal is exactly to catch a runaway script before it turns into an overnight surprise bill.