Hugging Face and OpenRouter join forces to make open-weight models easy to run
Hugging Face and OpenRouter join forces to make open-weight models easy to run
Hugging Face has switched its Inference Providers router to OpenRouter's, so requests to language models on the Hub are routed across 80+ providers based on live price, speed and reliability, with automatic retries on another provider if one fails, while code and pricing stay the same. The router supports OpenAI's Chat Completions and Responses APIs and Anthropic's Messages API, and model ids can carry suffixes like :fastest, :cheapest or a provider name to pick a policy. Hugging Face reports that open-weight models went from 26.8% of tokens served on OpenRouter in October 2025 to 71.7% at the end of September 2026, and that custom provider API keys no longer work for language models.
It documents a concrete routing and billing change for Hugging Face inference users, plus usage and cost data on open-weight versus closed models.
Source: Hugging Face Blog · huggingface.co