Hugging Face and OpenRouter join forces to make open-weight models
Back to Articles a]:hidden"> Hugging Face and OpenRouter join forces to make open-weight models easy to run Published November 16, 2026 Update on GitHub…
Summary
Back to Articles a]:hidden"> Hugging Face and OpenRouter join forces to make open-weight models easy to run Published November 16, 2026 Update on GitHub Upvote 11 +5 Célina Hanouti celinah Follow Victor Mustar victor Follow Bertrand Chevrier kramp Follow Lucain Pouget Wauplin Follow Pierric Cistac pierric Follow Eliott Coyac coyotte508 Follow Julien Chaumond julien-c Follow:last-child]:mb-0"> Hugging Face and OpenRouter are teaming up to make open-weight models easy to run. Every major open-weight release is already being published on the Hugging Face Hub, and OpenRouter serves those models at scale, routing each request across 80+ providers based on live measurements of each one. Together, every open-weight model on the Hub that a provider serves can be called with your Hugging Face token, through the same API, with the best provider picked for each request. Today, we are switching Inference Providers from our own custom router to OpenRouter's.
Positives
- Back to Articles a]:hidden"> Hugging Face and OpenRouter join forces to make open-weight models easy to run Published November 16, 2026 Update on GitHub Upvote 11 +5 Célina Hanouti celinah Follow Victor Mustar victor Follow Bertrand Chevrier kramp Follow Lucain Pouget Wauplin Follow Pierric Cistac pierric Follow Eliott Coyac coyotte508 Follow Julien Chaumond julien-c Follow:last-child]:mb-0"> Hugging Face and OpenRouter are teaming up to make open-weight models easy to run.
- Every major open-weight release is already being published on the Hugging Face Hub, and OpenRouter serves those models at scale, routing each request across 80+ providers based on live measurements of each one.
- Together, every open-weight model on the Hub that a provider serves can be called with your Hugging Face token, through the same API, with the best provider picked for each request.
- Today, we are switching Inference Providers from our own custom router to OpenRouter's.
Risks & concerns
- Requests made to language models now go through OpenRouter, which picks the best provider for each call based on live price, speed and reliability, and retries on another provider if the first one fails.