theaicatalog
Hugging Face ยท Products

Hugging Face moves its model routing to OpenRouter

Hugging Face and OpenRouter are teaming up so that every open-weight model on the Hugging Face Hub can be called with a Hugging Face token through one API. Hugging Face has switched its Inference Providers from its own router to OpenRouter's, which picks the best provider for each request based on live price, speed and reliability. OpenRouter routes requests across 80+ providers and retries another provider if the first one fails. Hugging Face says pricing does not change and it adds no markup, but users can no longer use their own API key for a provider on these language models.