Hugging Face moves its chat model routing to OpenRouter, with failover

TL;DR

  • On 16 November Hugging Face switched the chat models in Inference Providers from its own router to OpenRouter's, which picks a provider per call and retries on another if one fails.
  • Hugging Face says pricing doesn't change and it adds no markup, but you can no longer use your own provider API key with these language models.
  • OpenRouter says 160 models from 38 labs work this way, and it can now send a trace of each request to a Hugging Face Storage Bucket you own.

Read the full story

Sign in with your email to read AI News. It’s free.

Share this story

Explain like I’m 15