AWS Inferentia

Hardware

AWS's custom silicon for machine learning inference, purchased via Amazon EC2 Inf1 and Inf2 instances rather than as a standalone chip.

Find alternatives to AWS Inferentia

TypeHardware
RoleBundled component
AvailabilitySold
DeploymentPrivate cloud
Intended forDeveloper
SecurityNot recorded
StatusActive
Sold withinAmazon EC2 — Included with the parent
PricingUsage-based — official pricing ↗

What it does

aws.amazon.com

Sources

Pricing

Pricing page · 1 Sep 2026

Description

Official documentation · 1 Sep 2026

What it does

Official documentation · 1 Sep 2026

Sold within

Pricing page · 6 Sep 2026

Inferentia is not sold as a part: it is reached by renting the EC2 instance types built on it (Inf2, Trn1/Trn2), which are lines on EC2's own rate card. The chip has no price of its own anywhere on aws.amazon.com.

Name

Official documentation · 1 Sep 2026

URL

Official documentation · 1 Sep 2026

Interfaces

Official documentation · 12 Oct 2026

Page: 'AWS Neuron SDK helps developers deploy models on the AWS Inferentia chips'.

Intended for

Self-reported · 8 Sep 2026

Emphasizes integration with 'popular ML frameworks such as PyTorch and TensorFlow', positioning it for technical teams building inference applications.

Also from Amazon

Open Amazon in the directory

Something wrong here? Send a correction — quote this product id: aws-inferentia.