Hugging Face is routing language model requests through OpenRouter as of November 15, the company said.[1] The change means each request is sent to the provider with the best mix of price, speed and reliability based on live measurements, and retried elsewhere if it fails.[1] OpenRouter, which serves more than 800 trillion tokens a month across 600+ models from 80+ providers, recently rebuilt its routing to cut capacity errors by 46% and improve time to first token by 16.9% and throughput by 16.3%, according to Hugging Face.[1] Hugging Face and OpenRouter are teaming up to make open-weight models easy to run.[1]