The fastest Kwaipilot model is KAT-Coder-Pro V2 at 61 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 Kwaipilot model is KAT-Coder-Pro V2 at 61 output tokens per second.
modelgrep tracks 1 Kwaipilot models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by KAT-Coder-Pro V2. 1 of them qualify for this ranking.