Pipeline AI

Serverless GPU inference for ML models.

Pipeline gives you access to our Model Hub, a selection of pre-trained models. Simply submit a request to our REST API and you'll receive the output of the selected pipeline when the run completes.

This documentation outlines how to utilise our pre-trained models, but if you want to use our serverless API for your own ML models, we can help you! If you fill the form here, our team will reach out to you and help upload your model onto our API very quickly.

Key features

  • Access serverless GPU, this means no hourly rental fees, we charge on a pay-as-you-go basis. You can view our pricing here
  • Up-to-date enterprise hardware. Our cloud is constantly being upgraded with Ampere and Volta GPUs.
  • From a few requests to thousands, we handle the cloud infrastructure needed to run your ML models.

🛠️

Interested in deploying your own models with our serverless API?

Get a serverless inference endpoint for free here


Did this page help you?