Hugging Face Switches Model Chat Routing to OpenRouter
Hugging Face and OpenRouter have partnered, and model pages on Hugging Face now use OpenRouter's routing to pick a provider for chat.
1 source 5d ago
Reporting from 1 source: GIGAZINE.
Why it matters
Hugging Face is handing provider selection on its model pages to a third-party router, so the price and latency comparison users see is now OpenRouter's rather than Hugging Face's own.
Key Facts
- Hugging Face and OpenRouter have partnered to route chat on Hugging Face model pages through OpenRouter.
- The provider list on a Hugging Face model page shows pricing, latency, and uptime over the last 24 hours.
- OpenRouter CEO Alex Atallah said open-weight models' token usage on OpenRouter rose from 27% to 72% of the total over one year.
- Hugging Face CEO Clément Delangue said the partnership is about cooperation rather than competition in open source.
The provider list shows each option's pricing, latency, and 24-hour uptime, plus metrics for lowest price, fastest latency, longest context, and best uptime. OpenRouter CEO Alex Atallah said open-weight models' token share on OpenRouter rose from 27% to 72% over one year.
On a model page such as DeepSeek-V4.1-Flash-1017, the chat panel on the left now draws its provider through OpenRouter instead of Hugging Face's own routing system. Clicking Providers lists each provider with pricing, latency, and uptime over the last 24 hours, and the list can be switched freely. A separate Metrics view surfaces lowest price, fastest latency, longest context, and best uptime. Hugging Face CEO Clément Delangue framed the deal around cooperation, saying many people treat AI as a zero-sum game while open source is winning through cooperation rather than competition.
Written with AI by Yomimono from the 1 cited source below, including Japanese-language reporting where cited. See our editorial policy.
Add Yomimono as a preferred source on Google