Hugging FaceCélina Hanouti, Victor Mustar, Bertrand Chevrier, Lucain Pouget, Pierric Cistac, Eliott Coyac, Julien ChaumondAnnouncement
Hugging Face and OpenRouter join forces to make open-weight models easy to run
Summary
Hugging Face and OpenRouter are partnering to simplify running open-weight models. Hugging Face now routes language model requests through OpenRouter, which selects the best provider for each call based on live price, speed, and reliability, and retries on another provider if the first fails. The router supports OpenAI’s Chat Completions and Responses APIs and Anthropic’s Messages API for every chat model. Open-weight models on OpenRouter grew from 26.8% of tokens served in October 2025 to 71.7% by September 2026, and cost about four times less on average than closed models. Users pay the provider’s price on their Hugging Face bill with no markup, and can still pin a provider or policy via a model id suffix.
Context
Open-weight models have grown from 26.8% of tokens served on OpenRouter in October 2025 to 71.7% by September 2026, with weekly volume increasing more than 60-fold. Open-weight models cost about four times less on average than closed models, though the best open-weight models still trail proprietary ones on the hardest benchmarks.
Approach / What changed
Hugging Face replaced its own Inference Providers router with OpenRouter’s routing system, which selects the best provider for each request based on live measurements of price, speed, and reliability, and retries on another provider if the first one fails. Users call models through the same Hugging Face token and API, and can optionally pin a provider or policy via a model id suffix.
Takeaways
OpenRouter’s routing selects the best provider per request based on live price, speed, and reliability, and retries on another provider if the first fails.
Open-weight models on OpenRouter grew from 26.8% of tokens served in October 2025 to 71.7% by September 2026, with weekly volume increasing more than 60-fold.
Open-weight models cost about four times less on average: $0.28 per million input tokens and $1.62 per million output tokens, versus $1.27 and $6.36 for closed models.
FAQ
Does Hugging Face add a markup on OpenRouter-routed requests?
No. You pay the provider's price on your Hugging Face bill, and Hugging Face does not add a markup. PRO users get $2 of credits monthly, and Team and Enterprise organizations get $2 per seat.
Can I still use my own provider API key?
You can no longer use your own API key for a provider with language models, because requests are now billed to your Hugging Face account or organization. You can still pick a provider with a model id suffix or turn providers off in your settings.
Does the change affect image, video, or audio generation?
Image, video, and audio generation continue to work directly through Hugging Face Inference Providers without going through OpenRouter. You can keep using the same token and API, and access tens of thousands of LoRAs.
Source and freshness
- Source
- huggingface.co
- Published
- Added to Yomu
Summaries are generated from the original by a language model. Check the original before relying on it.
Keep reading
Related reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
The best engineering reads, once a week
One useful email. Unsubscribe anytime.