AIsaAIsaStudio 中文 Open AIsa Studio

Hugging Face and OpenRouter join forces to make open-weight models easy to run

Hugging Face has switched Inference Providers' language model routing to OpenRouter, which picks the best provider per request based on live price, speed and reliability, and retries on another provider on failure. The new routing cut capacity errors by 46%, improved time to first token by 16.9% and throughput by 16.3%; requests are billed to the Hugging Face account without markup, and custom provider API keys no longer work for language models.

Why it matters

An official announcement spelling out billing, supported APIs and the breaking change after the router switch, useful for developers adjusting existing calls.

Read the original ↗AI Daily, Nov 17

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.

Analysis

What happened

Hugging Face and OpenRouter have partnered, and Hugging Face's Inference Providers for language models now route through OpenRouter instead of its own custom router. Every open-weight model on the Hub that a provider serves can be called with a Hugging Face token through the same API.

Key details

  • OpenRouter picks the best provider per request based on live price, speed and reliability, and retries on another provider if the first one fails. Previously, Inference Providers picked one provider and returned its error on failure.
  • The router supports OpenAI's Chat Completions and Responses APIs and Anthropic's Messages API; users can pick a provider or policy via model id suffixes (e.g. :fastest, :cheapest, or a specific provider), and routing is cache-aware, keeping a conversation on the provider holding its prompt cache.
  • OpenRouter's rebuilt routing cut capacity errors by 46% and improved time to first token by 16.9% and throughput by 16.3%, based on its measurements.
  • Pricing is unchanged: users pay the provider's price with no markup; PRO users get $2 of monthly credits, Team and Enterprise get $2 per seat.
  • Image, video and audio generation still go directly through Hugging Face Inference Providers, not OpenRouter, and custom keys for image/video providers keep working.
  • Breaking change: language model requests are billed to the Hugging Face account or organization, so custom provider API keys no longer work for these models. New model-page tabs show Providers and Metrics; settings allow turning off providers per user or organization.

Why it matters

Open-weight model usage on OpenRouter grew from 26.8% of tokens served in October 2025 to 71.7% at the end of September 2026 (peaking at 77.5% in July), with weekly volume up more than 60-fold versus almost tenfold for closed models. The most used model on OpenRouter this week is the open-weight DeepSeek V4.1 Flash 1017 at 59.2 trillion tokens.

Open-weight models cost about four times less on average ($0.28 per million input tokens and $1.62 per million output tokens, versus $1.27 and $6.36 for closed models). On the Artificial Analysis Intelligence Index, the best open-weight model, Kimi K3.1 Pro, scores 46 against 65 for Claude Fable 5.2, at about a seventh of the cost per task ($3.68 versus $26.54). For many workloads, that trade-off is worth it, and simplified routing lowers the friction of running open-weight models at scale.

Who it affects

Developers using Hugging Face Inference Providers for language models: code stays the same, but custom provider keys stop working for these models and requests are billed to Hugging Face accounts. Organizations get shared provider settings, and future steps include connecting OpenRouter accounts and routing more tasks through OpenRouter.

Original article

Hugging Face and OpenRouter are teaming up to make open-weight models easy to run. Every major open-weight release is already being published on the Hugging Face Hub, and OpenRouter serves those models at scale, routing each request across 80+ providers based on live measurements of each one. Together, every open-weight model on the Hub that a provider serves can be called with your Hugging Face token, through the same API, with the best provider picked for each request.

Today, we are switching Inference Providers from our own custom router to OpenRouter's. Requests made to language models now go through OpenRouter, which picks the best provider for each call based on live price, speed and reliability, and retries on another provider if the first one fails. Your code stays the same.

Run them with the tools you already use

The router supports OpenAI's Chat Completions and Responses APIs and Anthropic's Messages API for every chat model, whatever the provider behind it. Pick your coding agent or SDK and a model, then copy the steps, or copy the whole setup as a prompt for your agent:

Setup guides for Claude Code, Codex, OpenCode, Pi and Hermes Agent

The same Hugging Face token also gives you storage with Storage Buckets, compute with Jobs and dedicated inference with Inference Endpoints. PRO, Team and Enterprise plans include monthly credits for compute and inference.

How open-weight models are used

On OpenRouter, open-weight models went from 26.8% of the tokens served in October 2025 to 71.7% at the end of September 2026, after peaking at 77.5% in July (OpenRouter, October 2026). Over the same period, weekly open-weight volume grew more than 60-fold, against almost tenfold for closed models. This week, the most used model on OpenRouter is an open-weight one, DeepSeek V4.1 Flash 1017, with 59.2 trillion tokens (rankings).

Open-weight models' share of tokens on OpenRouter, from 26.8% in October 2025 to 71.7% in September 2026 Open-weight models' share of tokens on OpenRouter, from 26.8% in October 2025 to 71.7% in September 2026

Open-weight models cost about four times less on average: $0.28 per million input tokens and $1.62 per million output tokens, against $1.27 and $6.36 for closed models.

The best open-weight models still trail the best proprietary ones on the hardest benchmarks. On the Artificial Analysis Intelligence Index, Kimi K3.1 Pro, the best open-weight model, scores 46 against 65 for Claude Fable 5.2, at about a seventh of the cost per task ($3.68 against $26.54). For a lot of workloads, that trade-off is worth it.

Artificial Analysis Intelligence Index against cost per task, for the top proprietary and open-weight models Artificial Analysis Intelligence Index against cost per task, for the top proprietary and open-weight models

Routing powered by OpenRouter

OpenRouter serves more than 800 trillion tokens a month to over 10 million users, across 600+ models from 80+ providers. Its routing is based on live measurements of every provider across that traffic.

OpenRouter recently rebuilt its provider routing: instead of only looking at the lowest list price, it sends each request to the provider with the best mix of price, speed and reliability.

When a provider slows down or starts failing, traffic moves away from it until it recovers, and a failed try is retried on the next best provider inside the same call. In OpenRouter's measurements, the new routing cut capacity errors by 46% and improved time to first token by 16.9% and throughput by 16.3%.

Default routing retries on another provider when the first one is rate limited, :cheapest picks the lowest price and :fastest the highest throughput Default routing retries on another provider when the first one is rate limited, :cheapest picks the lowest price and :fastest the highest throughput

Before, Inference Providers picked one provider for your request and returned its error if it failed. Now, the request is retried on another provider. You can still choose a policy or a provider with a suffix on the model id:

zai-org/GLM-5.3            # default: best mix of price, speed and reliability
zai-org/GLM-5.3:fastest    # highest throughput
zai-org/GLM-5.3:cheapest   # lowest price
zai-org/GLM-5.3:novita     # only Novita

Routing is also cache-aware: a conversation stays on the provider that holds its prompt cache. To make it explicit, send a stable UUID per conversation in the X-HF-Session-Id header (see the prompt caching guide).

Pricing

Pricing doesn't change: you pay the provider's price on your Hugging Face bill, and Hugging Face doesn't add a markup on top of it. PRO users get $2 of credits every month, and Team and Enterprise organizations get $2 per seat. See Pricing and Billing for the details.

Image, video and audio generation

Image, video, and audio generation continue to work exactly as before, directly through Hugging Face Inference Providers without going through OpenRouter. You can keep using the same token and API, and access tens of thousands of LoRAs.

See where your requests go

On model pages, you can chat with the model right away in the widget. Two new tabs show what's behind it: Providers lists every provider OpenRouter can route the model to, with its input and output price, speed and uptime over the last 24 hours, and Metrics shows the best price, throughput, time to first token, context length and uptime among them:

Chatting with Inkling-2-Small in the model page widget, opening its code snippets, then its Metrics tab Chatting with Inkling-2-Small in the model page widget, opening its code snippets, then its Metrics tab

Your usage overview breaks your spend down by the provider each request went to:

Daily Inference Providers spend, broken down by provider Daily Inference Providers spend, broken down by provider

In your settings, you can turn off any provider you don't want: the router never sends your requests there. Organizations have the same settings, and they apply to every request billed to the organization.

Inference Providers settings, with a toggle for each provider Inference Providers settings, with a toggle for each provider

Breaking change: custom provider keys

Requests to language models now go through OpenRouter and are billed to your Hugging Face account or organization, so you can no longer use your own API key for a provider with these models. You can still pick a provider with a suffix on the model id (model:provider) or turn providers off in your settings, and your code stays the same. Custom keys for image and video providers keep working.

What's next

This is the first step of our partnership with OpenRouter. Next:

  • Connect your OpenRouter account to Hugging Face.
  • More tasks routed through OpenRouter.

Try a model, or read the Inference Providers docs to get started.

The original belongs to Hugging Face Blog and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.

Other coverage 2