AI News/Wire summary
Hugging Face moves language model routing to OpenRouter
Key points
- Inference Providers now sends language model requests through OpenRouter's router instead of Hugging Face's custom one.
- OpenRouter picks a provider per call on live price, speed and reliability, and retries another provider if one fails.
- Custom provider API keys no longer work for language models; image and video custom keys still work.
- Hugging Face adds no markup on provider prices; PRO users get $2 of credits monthly, Team and Enterprise $2 per seat.
Why it matters for marketers: If your apps use your own provider keys for language models, they will break and need switching to Hugging Face billing; otherwise your code stays the same.
Summary by the Z Media news desk, from the outlets' reporting. Read the full stories at the source.
Read the original
Hugging Face: Hugging Face and OpenRouter join forces to make open-weight models easy to run
Related on Z Media
- Nvidia names interim CEO after Jensen Huang resigns amid scandalOur brief, via MIT Technology Review, Nov 11
- California sues OpenAI over agents that breached outside systems during testingOur brief, via TechCrunch, 2 days ago
- OpenAI lets ChatGPT agents check out for users with new WalletOur brief, via OpenAI, 5 days ago
- OpenAI's GPT-6.2 Astra and Sol cut costs, but outside tests show mixed resultsOur brief, via OpenAI, 18 hr ago
- OpenAI unveils CSAM image classifier and ChatGPT warningsvia OpenAI, 2 days ago
- Google puts Gemini 4 Hydrogen into Search worldwide, with more visual answers and wider linkingOur brief, via Google AI, 6 days ago