Hugging Face Integrates OpenRouter to Route Open-Weight Models
Hugging Face integrated OpenRouter into its platform, switching its Inference Providers from a custom router to OpenRouter's routing system. Requests to language models now go through OpenRouter, which selects providers based on live price, speed and reliability, while users keep the same token and endpoint. Hugging Face also added live model stats on the Hub and a redesigned inference widget.
Event version 1.
Key insights
Routing switched to OpenRouter
Hugging Face switched Inference Providers from its own custom router to OpenRouter's. OpenRouter picks the best provider for each call based on live price, speed and reliability, and retries on another provider if the first fails.
Same token and endpoint
Every open-weight model on the Hub that a provider serves can be called with a Hugging Face token through the same API. The router supports OpenAI's Chat Completions and Responses APIs and Anthropic's Messages API for every chat model.
Open-weight usage share rose
On OpenRouter, open-weight models went from 26.8% of tokens served in October 2025 to 71.7% at the end of September 2026, peaking at 77.5% in July. Weekly open-weight volume grew more than 60-fold over the period, against almost tenfold for closed models.
Cost gap between open and closed models
Open-weight models cost about four times less on average: $0.28 per million input tokens and $1.62 per million output tokens, against $1.27 and $6.36 for closed models. On the Artificial Analysis Intelligence Index, Kimi K3.1 Pro scores 46 against 65 for Claude Fable 5.2 at about a seventh of the cost per task.
OpenRouter routing scale
OpenRouter serves more than 800 trillion tokens a month to over 10 million users across 600+ models from 80+ providers. Its rebuilt routing sends each request to the provider with the best mix of price, speed and reliability rather than only the lowest list price.