Hugging Face and OpenRouter join forces to make open-weight models easy to run
Hugging Face and OpenRouter have partnered to route language model inference through OpenRouter, replacing Hugging Face's custom router. The new system dynamically selects the best provider for each request based on price, speed, and reliability, while maintaining the same API and user pricing. OpenRouter's usage statistics indicate a significant shift toward open-weight models, which now account for the majority of tokens served on the platform. Open article →