The fastest Relace model is Relace Search at 10 output tokens per second.
AI models ranked by output speed (tokens per second, p50). The fastest large language models for low-latency and high-throughput applications.
The fastest Relace model is Relace Search at 10 output tokens per second.
modelgrep tracks 2 Relace models with live benchmarks, speed, latency and per-provider pricing. 1 of them qualify for this ranking.