Inference Endpoints (dedicated) documentation

Access πŸ€— Inference Endpoints

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Access πŸ€— Inference Endpoints

To access the Inference Endpoints web application, you or your organization need to add a valid payment method to your Hugging Face account.

You can check your [billing](https://huggingface.co./settings/billing) if you're unsure whether you have an active payment method.

There are two pricing plans:

  • Inference Endpoints pricing is based on your hourly compute, and billed monthly. This can be as low as $0.032 per CPU core/hr and $0.5 per GPU/hr depending on your needs.
  • There is also an Enterprise plan for Inference Endpoints which offers dedicated support, 24/7 SLAs, and uptime guarantees. Pricing for Enterprise is custom and based on volume commit and annual contracts; contact us for a quote if interested!

After you’ve added a valid payment method to your account, access the Inference Endpoints web application and start deploying! πŸ₯³

< > Update on GitHub