LLM Benchmarks Engineering Teams Can Act On
Pick models by cost per token, latency at P95, and performance on your actual tasks.
Nadia Nair
Staff Writer
Nadia Nair is a staff writer at LLM Router Stack covering model routing strategy. Based in Montréal, Nadia has written for LLM Router Stack since 2023.
1 story · Montréal
Pick models by cost per token, latency at P95, and performance on your actual tasks.