# Hugging Face routes language model calls through OpenRouter

> Developers’ code stays the same, but requests now use OpenRouter to pick the cheapest, fastest or most reliable provider.

Oossa · 2026-11-18 · https://oossa.com/en/hugging-face-routes-language-model-calls-through-openrouter

Hugging Face announced on November 18, 2026 that its Inference Providers service will send all language‑model requests through OpenRouter. The change is automatic; existing API calls keep working without code changes. By default the router selects a provider that balances price, speed and reliability, but developers can add a suffix like ":fastest" or ":cheapest" to force a specific priority, or name a provider directly. A new "X‑HF‑Session‑Id" header lets the router keep a conversation on the same provider’s cache, improving response time for ongoing chats.

## What the new routing does

OpenRouter measures every provider in real time and switches to another one if the first slows down or fails. According to OpenRouter’s own tests, the new routing cut capacity errors by 46 %, shaved 16.9 % off the time to first token, and lifted overall throughput by 16.3 %. Hugging Face passes the provider’s price straight through to users, adding no markup. Pro plans get a $2 monthly credit, and Team or Enterprise plans receive $2 per seat.

## Impact on open‑weight models

Open‑weight (open‑source) models now dominate the traffic on OpenRouter, accounting for about 71 % of tokens processed by the end of September 2026, up from 26.8 % in October 2025. Open models cost roughly a quarter of what closed models charge per million tokens – about $0.28 in versus $1.27 for input, and $1.62 out versus $6.36. The best open model, Kimi K3.1 Pro, scores 46 on the Artificial Analysis Intelligence Index, while the top proprietary model, Claude Fable 5.2, scores 65 but costs about seven times more per task.

## The facts

- The routing change was announced on November 18, 2026 – "Wed Nov 18 2026 15:33:44 GMT+0100".
- OpenRouter processes over 800 trillion tokens per month for more than 10 million users.
- Capacity errors fell 46 % and time‑to‑first‑token improved 16.9 % after the routing update.
- Open‑weight models made up 71.7 % of tokens on OpenRouter by September 2026, up from 26.8 % in October 2025.
- Open models cost about $0.28 per million input tokens and $1.62 per million output tokens, versus $1.27 and $6.36 for closed models.

## Why it matters

Developers can keep their existing code but get faster, cheaper responses automatically, which reduces operating costs for apps that use chat models. Users of open‑source models benefit from lower prices while still accessing the same API, making AI services more affordable for small teams and hobbyists.

## Sources & references

1. [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
2. [Hugging Face](https://huggingface.co/blog/openrouter?utm_source=openai) – Hugging Face
3. [OpenRouter](https://openrouter.ai/blog/announcements/hugging-face-inference-providers/?utm_source=openai) – OpenRouter

Last updated: 2026-11-18
