Dedicated Inference

A service for deploying pre-configured ML models with a ready-to-use API in Selectel infrastructure. Models are deployed as separate inference services

View on website

Key product info

General information

Basic information about Dedicated Inference: description, billing model, and pricing

Availability across locations

Regions and pools where Dedicated Inference is available

Users and roles

How to restrict access to an account and resources using user types and their roles

Projects

How projects work, how to create a project, and how to grant access to it

Project limits and quotas

How to configure resource consumption limits

All about the product

Overview

Basic information about Dedicated Inference: description, billing model, and prices

Quickstart

How to get started with Dedicated Inference: create an inference service and connect to it

Create an inference service

How to choose a suitable configuration, description of model parameters and metrics, and how to create an inference service

Work with inference service

How to scale an inference service, manage API keys, examples of connecting to an inference service

Release notes

Dedicated Inference updates

Additional materials

Practical ML course

Useful materials on running ML models and efficiently allocating compute resources

Building ML workflows

Useful materials for companies implementing machine learning into their workflows

Blog articles

Selectel expert insights, technical reviews, and case studies

Academy tutorials

Working with popular tools

Academy courses

Materials for learning how to work with products