TOMORROW’S TECH
← Chips & Compute

AWS Trainium2

AWS · #6 most active of 18 in Chips & Compute

Compare →

Trn2 UltraServers and Project Rainier capacity, programmed through the Neuron SDK.

Current version

Trainium2

Entry cost

from ~$1.3 per accelerator-hour

Changes / 30d

0

Capabilities

  • Trn2 UltraServer
  • 64-chip NeuronLink domain
  • Neuron SDK
  • Rainier cluster

Pricing

from ~$1.3 per accelerator-hour

Entry price over time

Not enough pricing history yet — we start charting from the second observation.

Geek mode

Models under the hood

  • Trainium2

    AWS

    disclosed

  • Neuron compiler

    AWS

    disclosed

Context window

—

Public API

yes

Multi-model routing

no

Stack signals

  • Neuron SDK
  • PyTorch XLA
  • JAX
  • EFA networking

Shared model stack

Other tracked products running on the same foundation models — a quick read on how much of the catalog moves when one of these models changes.

green disclosed · amber inferred · grey unknown

Reported scale

Reference data. Each figure is whatever the source actually said — weekly users, downloads, revenue run-rate — with its own definition and date. These are not comparable between tools and are never used to rank anything.

No public usage figure on record for this product.

Also in Chips & Compute

All Chips & Compute
Cerebras WSE-3

Cerebras

1

Wafer-scale inference and training

Version
WSE-3 / Inference
Cost
Free tier, then from $0.06 / M tokens
Model
Llama / Qwen / GPT-OSS
Google TPU Ironwood

Google

1

Inference-first TPU pods

Version
v7 Ironwood
Cost
from ~$1.2 per chip-hour
Model
TPU v7
Groq LPU

Groq

1

Deterministic low-latency inference

Version
GroqCloud
Cost
Free tier, then from $0.05 / M tokens
Model
Llama / Kimi / GPT-OSS
AMD Instinct MI355X

AMD

High-memory GPU alternative

Version
MI355X
Cost
~$2-3 per GPU-hour on clouds
Model
CDNA 4
Apple Silicon Neural Engine

Apple

On-device inference across Mac, iPhone and iPad.

Version
M5
Cost
Bundled with hardware
Model
Apple Foundation Models
Broadcom custom accelerators

Broadcom

Co-designed XPUs behind most hyperscaler silicon.

Version
2025
Cost
Enterprise supply agreements
Model
powers Google TPU

Change history

  • capability

    Trn2 UltraServers open to general customers

    —64-chip NeuronLink domain

    source