# “Collaboration over competition”: Hugging Face hands model inference traffic to OpenRouter

Source: [The New Stack](https://thenewstack.io/hugging-face-openrouter-inference/) · 2026-11-18 · Cloud & DevOps
Page: https://themorning.dev/story/collaboration-over-competition-hugging-face-hands-model-inference-traffic-to-ope-516badfab0c84247
Kind: business · Impact: medium

## In brief

- Hugging Face now routes language model inference requests through OpenRouter, which selects the cheapest or fastest provider.
- Bring-your-own API keys for language models are being discontinued.
- According to OpenRouter, the new routing cut capacity errors by 46 percent.

## Why it matters

Developers using Hugging Face for language model inference will have requests served by OpenRouter's provider routing, and they can no longer use their own API keys for these models.

## What to do

- Check whether your integration uses your own provider API keys for language models, since that option is going away.

## Coverage

- [Hugging Face now routes model requests through OpenRouter for the best price or speed](https://the-decoder.com/hugging-face-now-routes-model-requests-through-openrouter-for-the-best-price-or-speed/) — The Decoder, 2026-11-18
- [“Collaboration over competition”: Hugging Face hands model inference traffic to OpenRouter](https://thenewstack.io/hugging-face-openrouter-inference/) — The New Stack, 2026-11-18

Tags: inference, hugging-face, openrouter, llm-routing, api

---

Brief generated by AI (claude-haiku-5-5) from the reporting listed under Coverage. Headlines belong to their publishers. The Morning Dev – https://themorning.dev
