Hugging Face moves Inference Providers onto OpenRouter's router: open-weight models served by 80+ providers are callable with one Hugging Face token, with no markup
Open models on the Hub are now routed by OpenRouter, which picks a provider for each request and retries on another when one fails. How routing is chosen, how prompt caches are kept, billing, and one breaking change, for teams calling open models through an API.
// Key points
- Language model requests through Inference Providers now go through OpenRouter, which picks a provider per call on live price, speed and reliability and retries on the next one inside the same call if the first fails. It supports OpenAI's Chat Completions and Responses APIs and Anthropic's Messages API.
- A suffix on the model id selects a policy or provider (such as :fastest, :cheapest or :novita). Routing is cache-aware: a stable UUID per conversation in the X-HF-Session-Id header keeps it on the provider holding its prompt cache. OpenRouter says the new routing cut capacity errors by 46% and improved time to first token by 16.9% and throughput by 16.3%.
- Pricing is unchanged: you pay the provider's price on your Hugging Face bill with no markup, and PRO users get $2 of monthly credits. Breaking change: you can no longer use your own provider API key for language models; custom keys for image and video providers still work.
- Figures cited: open-weight models went from 26.8% of tokens on OpenRouter in October 2025 to 71.7% at the end of September 2026, and average $0.28 input and $1.62 output per million tokens, against $1.27 and $6.36 for closed models.
Builder's takeI would route PandaClaws' less quality-sensitive batch rewriting through the :cheapest suffix for a week and compare cost per task and rework rate with the closed model it uses now. Teams already using their own provider keys on Inference Providers need to sort out billing first, since this is a breaking change; for multi-turn chats, send the session id or cache hits will drop.
// Background · from #Open models
Full timeline →- Nov 17 Open-weight models on Amazon Bedrock now support explicit prompt caching alongside implicit caching, through the Chat Completions API
- Nov 17 NVIDIA's provisional MLPerf Endpoints v1.0 results: Vera Rubin NVL72 delivers 5x to 10x the throughput per kilowatt of GB300 NVL72 on agentic inference
- Nov 16 tiny-voca is released under Apache 2.0: a 4.5M-parameter English TTS model that runs about 70x faster than real time on four CPU threads