Inference Providers routing through OpenRouter
Hugging Face switched Inference Providers for language models from its own router to OpenRouter, so one Hugging Face token reaches open-weight models across 80+ providers with automatic retries.
Language model requests now go through OpenRouter, which picks a provider per call based on live price, speed and reliability and retries on another provider if one fails. The router supports OpenAI Chat Completions and Responses APIs and Anthropic's Messages API for every chat model. Image, video and audio generation still run directly through Hugging Face Inference Providers, and custom provider keys no longer work for language models.
- Date
- Monday 16 November 2026
- Lab
- Hugging Face
- Kind
- feature
- Access
- closed API
- Price
- No change: you pay the provider's price on your Hugging Face bill with no markup. PRO users get $2 of credits monthly, Team and Enterprise get $2 per seat.
Figures
| Measure | Value | Measured by |
|---|---|---|
| Capacity errors reduction with new OpenRouter routing | 46% also 16.9% better time to first token and 16.3% better throughput | OpenRouter |
| Open-weight share of tokens on OpenRouter | 71.7% at end of September 2026 up from 26.8% in October 2025, peak 77.5% in July | OpenRouter |
| Average price of open-weight models per million input/output tokens | $0.28 / $1.62 closed models $1.27 / $6.36 | OpenRouter |
Breaking change: custom provider API keys no longer work for language models. Described as the first step of the partnership, with OpenRouter account linking next.
Sources
This record was checked against its sources on 16 November 2026. How we check