In the news
Hugging Face and OpenRouter join forces to make open-weight models easy to run
Hugging Face · Published · 3 min read
In 30 seconds
- What happened
- Hugging Face switched its Inference Providers routing to OpenRouter, which now selects the best provider across 80+ services for each request based on live price, speed, and reliability.
- Why it matters
- Engineers using Hugging Face's inference API for language models benefit from automatic provider selection and improved reliability without changing their code or token.
- Watch out
- Custom provider API keys no longer work for language models through Hugging Face; requests now route through OpenRouter and bill to your Hugging Face account instead.
- open-weight
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.