Realtime AI News
Hugging Face hands model routing to OpenRouter to make open weights turnkey
Hugging Face has switched its Inference Providers service from a custom router to OpenRouter, which picks a provider for each call based on live price, speed and reliability and retries elsewhere on failure, with no code changes for developers. The two companies describe the move as the first step of a partnership aimed at making open-weight models as easy to call as closed APIs.

Hugging Face has handed the routing layer of its Inference Providers service to OpenRouter, replacing its own custom router with a third-party system that decides, request by request, which provider should serve a model. The company announced the change in a blog post published on November 16, describing it as the first step in a partnership between the two firms.
Under the new setup, calls to language models pass through OpenRouter, which selects a provider based on live price, speed and reliability and retries on a second provider if the first one fails. Hugging Face says existing code does not need to change, and the router supports OpenAI's Chat Completions and Responses APIs as well as Anthropic's Messages API for every chat model, regardless of which provider sits behind it. The post also walks through setup for agents including Claude Code, Codex and OpenCode.
The company framed the move as a bet on open weights. Citing OpenRouter data, it says open-weight models grew from 26.8% of the tokens served on the platform in October 2025 to 71.7% at the end of September 2026, after peaking at 77.5% in July. Weekly open-weight volume grew more than 60-fold over the same period, against roughly tenfold for closed models.
Cost is a large part of the appeal. The post puts average open-weight pricing at $0.28 per million input tokens and $1.62 per million output tokens, against $1.27 and $6.36 for closed models — roughly a quarter of the price. Hugging Face does not pretend the trade-off is free, noting that the strongest open-weight models still trail the best proprietary systems on the hardest benchmarks.
OpenRouter brings scale to the arrangement. Hugging Face says the company serves more than 800 trillion tokens a month to over 10 million users, across more than 600 models from over 80 providers, and that OpenRouter recently rebuilt its routing so that it weighs speed and reliability alongside list price. In OpenRouter's own measurements, the new routing cut capacity errors by 46% and improved time to first token by 16.9% and throughput by 16.3%.
Developers keep some control. A suffix on the model ID can pin a request to the fastest provider, the cheapest one, or a named provider, and routing is cache-aware so a conversation stays with the provider holding its prompt cache; a stable session-ID header makes that explicit. Pricing does not change — users pay the provider's price on their Hugging Face bill, with no markup — and PRO users still get $2 of monthly credits.
There is one breaking change. Because language-model requests are now billed through Hugging Face accounts, customers can no longer bring their own provider API key for those models, although custom keys for image and video providers keep working, and image, video and audio generation still run directly through Hugging Face. The company said more stages of the partnership are coming.
Why it matters
For developers, calling an open-weight model stops being a procurement problem and becomes an ordinary API call, with failover handled in the routing layer. For model providers, joining the pool means competing on measured price, latency and uptime rather than on list price alone.
Nearby Updates
All11/16, 08:00
The King's Trust and OpenAI launch £1m partnership to reach 25,000 young people
The King's Trust and OpenAI have launched a £1 million partnership intended to help up to 25,000 young people across the UK build practical AI skills for work. The announcement fixes both the funding figure and a reach target, putting the emphasis on employability rather than on product news.
11/16, 08:00
AI Day Seoul wraps with 2,000-plus attendees focused on physical AI and agents
Nvidia's event recap says AI Day Seoul drew more than 2,000 attendees to COEX over two days, bringing together Korean industry leaders, startups and developer communities around physical AI and AI agents. At the plenary, Nvidia robotics and edge AI vice president Deepu Talla said Korea is punching above its weight in the field.
11/16, 07:30
Indian chip startup Bharat Semi raises $24M seed to target global AI sensor market
Bharat Semi, an Indian chip startup, has raised a $24 million seed round as it targets the global market for AI-enabled sensors. The company says it has secured design wins for its AI sensor technology with customers including General Atomics.
11/16, 09:27
Anthropic's record IPO faces big questions before it reaches the market
France 24 reports that Anthropic's record-breaking IPO is heading toward the public markets while still facing a set of big questions. Rather than treating the listing as a settled triumph, the report frames the offering as a test of what a leading AI company must prove once its valuation is priced daily by public investors.