Hermes Vector

Tech

Hugging Face and OpenRouter partner to simplify open-weight model access

Hugging Face is switching its Inference Providers router to OpenRouter, allowing open-weight models on the Hugging Face Hub to be called with a Hugging Face token through a single API.

By Hermes Vector

Checked against 1 sourceHugging Face
Illustration for: Hugging Face and OpenRouter partner to simplify open-weight model access

In brief

  • Hugging Face and OpenRouter are partnering to make open-weight models easy to run.
  • Inference Providers now routes language model requests through OpenRouter using live price, speed and reliability measurements.
  • Users can call open-weight models on the Hugging Face Hub with a Hugging Face token through a single API.
  • Custom provider keys for language models no longer work; requests are billed to the Hugging Face account or organization.

Hugging Face and OpenRouter partner to simplify open-weight model access

Partnership and routing change

Hugging Face and OpenRouter are teaming up to make open-weight models easy to run. Every major open-weight release is 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 a Hugging Face token, through the same API, with the best provider picked for each request.

Today, Hugging Face is switching Inference Providers from its 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. User code stays the same.

How it works

The router supports OpenAI's Chat Completions and Responses APIs and Anthropic's Messages API for every chat model, whatever the provider behind it. The same Hugging Face token also gives users 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.

Users 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, users can send a stable UUID per conversation in the X-HF-Session-Id header.

Pricing and breaking change

Pricing doesn't change: users pay the provider's price on their 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.

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

A breaking change affects custom provider keys: requests to language models now go through OpenRouter and are billed to the user's Hugging Face account or organization, so users can no longer use their own API key for a provider with these models. Users can still pick a provider with a suffix on the model id or turn providers off in their settings. Custom keys for image and video providers keep working.

Why it matters

The partnership lets developers call open-weight models on the Hugging Face Hub with a single Hugging Face token, while OpenRouter handles provider selection, retries and caching across more than 80 providers. Hugging Face says this is the first step of its partnership with OpenRouter, with plans to connect OpenRouter accounts to Hugging Face and route more tasks through OpenRouter.


Sources

This article was drafted with AI assistance and checked against the sources above. Company claims are reported as claims. Cover image is AI-generated.

The day's checked news, by email

One short email a day with the top stories. Free, and you can unsubscribe in one click.

Or follow for the latest news:

How do you feel about this story?

Comments 0

No comments yet. Start the discussion.