Today ainotis Join

My notis

ToolingPublished All news from that day

Hugging Face moves language-model routing for Inference Providers to OpenRouter, and ends custom provider keys for those models

Hugging Face's 16 November post says prices are unchanged and no markup is added, but language-model requests are now billed to the Hugging Face account.

Share

Check our sources · 6 facts from 1 source

Hugging Face switched the language-model routing of its Inference Providers from its own router to OpenRouter, it said in a blog post on 16 November. OpenRouter picks a provider for each call based on live price, speed and reliability, and retries on another provider if the first fails.

One thing breaks: language-model requests are billed to the Hugging Face account or organisation, so a user can no longer bring their own provider API key for those models. Custom keys for image and video providers still work, and image, video and audio generation still go directly through Hugging Face.

Hugging Face says prices are unchanged, with the provider's price passed on and no markup. Users can add a suffix such as :fastest, :cheapest or a provider name to choose a policy, and the router supports the OpenAI Chat Completions and Responses APIs and the Anthropic Messages API.

Share this story

Your reaction

We count reactions per story and day, never who reacted. The counts help us choose what goes in the monthly issue. If you are signed in, your own page shows yours too.

Check our sources

Every sentence above is checked against this source.

1 Hugging Face and OpenRouter join forcesHugging Face · 16 Nov 2026 · 6 facts Open the source archived copy
  1. Hugging Face announced on 16 November 2026 that its Inference Providers language-model routing now goes through OpenRouter instead of its own router.

    Today, we are switching Inference Providers from our own custom router to OpenRouter's.
    cite
  2. OpenRouter picks a provider for each call based on live price, speed and reliability, and retries on another provider if the first fails.

    picks the best provider for each call based on live price, speed and reliability
    cite
  3. Language-model requests are billed to the user's Hugging Face account or organisation, so users can no longer use their own provider API key for these models; custom keys for image and video providers still work.

    can no longer use your own API key for a provider with these models. Custom keys for image and video providers keep working.
    cite
  4. Hugging Face says prices are unchanged: users pay the provider's price on their Hugging Face bill with no markup.

    Pricing doesn't change: you pay the provider's price on your Hugging Face bill.
    cite
  5. A model-id suffix such as :fastest, :cheapest or a provider name selects a routing policy, and the router supports OpenAI Chat Completions and Responses and the Anthropic Messages APIs for every chat model.

    The router supports OpenAI's Chat Completions and Responses APIs and Anthropic's Messages API
    cite
  6. Image, video and audio generation still go directly through Hugging Face Inference Providers, not OpenRouter.

    directly through Hugging Face Inference Providers without going through OpenRouter
    cite

Topics

The morning email

On the mornings we publish: the three top stories and up to four short ones. Free.

We email you a link to confirm. An issue may include one sponsor, always labelled Sponsored · Advertisement. Our emails count opens and clicks, not who made them. Unsubscribe in one click. What we keep