Kovara Accelerator Intelligence / GPU0103

NVIDIA

H100 NVLink 80GB — Hyperstack flavor

Hopper
Hopper
80 GB VRAM
Previous

Explore Compute Compare Offerings Request Compute Official Product Page (opens in a new tab)

Live offerings: 2
Providers: 1
Regions: 1
Comparable price range: $1.82–$2.60USD / GPU-hour
Latest checked: 29 Sept 2026

Accelerator Overview

Core hardware and lifecycle, drawn from Kovara master data.

Core hardware

Architecture: Hopper
Generation: Hopper
VRAM: 80 GB

Lifecycle / usage

Primary use: AI training / inference / HPC
Launch year: 2022
Generation status: Previous
Last verified: 25 Sept 2026

Market Intelligence

Public Kovara observations; not a claim of complete or universal market coverage. Incompatible raw price units are excluded.

Observed GPU-hour range

USD / GPU-hour

Low: $1.82
Median: $2.21
High: $2.60

Spread $0.78 USD / GPU-hour

Comparable observations: 4
Providers observed: 1
Regions observed: 1
Last observed: 29 Sept 2026

Monitor this GPU →

Provider Coverage

Providers represented by current Kovara-tracked offerings.

Hyperstack

2 live offerings · 1 tracked regions

Availability unconfirmed 1 · Unconfirmed 1

Lowest comparable$1.82 USD / GPU-hour

Provider profile →Filtered compute →

Regional Coverage

Regions represented by current offerings; this does not describe complete global availability.

Unspecified, Multiple / Unspecified

2 live offerings · 1 providers

Lowest comparable$1.82 USD / GPU-hour

Region profile →

Offering Intelligence

Current configurations, recorded availability, confirmed capacity and the evidence behind each price.

Explore on Compute →

Current public compute offerings, in existing price order
Provider	Region	Configuration	Availability	Price	Commercial model	Trust / evidence	Action
OFR-0703Hyperstack	Unspecified, Multiple / Unspecified	NVIDIA H100 NVLink 80GB — Hyperstack flavorConfiguration quantity not specified	Availability unconfirmedConfirmed capacity: Not confirmed	$1.82 USD / GPU-hourOriginal: USD 1.82 GPU/hour from	ReservedGPU VM · Starting hourly reservation rate	Confidence AChecked todayConfirmed 29 Sept 2026Source: SRC000002	Inspect
OFR-0702Hyperstack

Technical Specifications

Recorded hardware attributes. Not tracked is distinct from No.

Compute

Architecture: Hopper
Generation: Hopper
Primary use: AI training / inference / HPC

Memory

VRAM: 80 GB

Platform

NVLink supported: Yes
MIG supported: Yes

Lifecycle / usage

Primary use: AI training / inference / HPC
Launch year: 2022
Generation status: Previous
Last verified: 25 Sept 2026

Data & Evidence

Public evidence and confidence signals supporting Kovara-tracked coverage.

Public source records: 1
Latest checked / observed: 29 Sept 2026
Comparable observations: 4

Source types: Pricing Page
Source reliability: A 1
Offering confidence: A 2
Observation confidence: A 4

Loading your page…

Core hardware

Lifecycle / usage

Hyperstack

Unspecified, Multiple / Unspecified

Compute

Memory

Platform

Lifecycle / usage

NVIDIA H100 80GB — provider does not specify PCIe/SXM

NVIDIA H100 NVL 94GB

NVIDIA H100 PCIe 80GB

NVIDIA H100 SXM