Hacker News new | ask | show | jobs
by santiago-pl 7 days ago
GoModel author here. I prepared self-reproducible benchmarks and published them on my blog. Might be helpful. I don't think latency is the best metric for comparing AI gateways, as most of the latency comes from the providers. Memory usage is a much better metric and GoModel wins here.

https://enterpilot.io/blog/benchmarking-ai-gateways-gomodel-...