What the marketis actually doing.
Observed secondary-market GPU price ranges. The monthly reading is dated October 1, 2026; later additions carry their own dates below.
Secondary market pricing for enterprise GPUs
Ranges reflect current availability and condition across the active catalog.
Generation bands
Hopper
4 models
$26,875to$41,928
Ampere
7 models
$908to$18,879
Ada
4 models
$2,252to$8,750
$908
Entry point
$41.9K
Top of range
15
Models priced
H100 NVL
Hopper94GB / NVL
Paired NVL cards with extra memory for big-model inference.
Market range
$29,900to$41,928
H200 NVL
Hopper141GB / NVL
Hopper with 141GB HBM3e for large-model inference in PCIe servers.
Market range
$26,875to$34,799
H100 PCIe
Hopper80GB / PCIe
Drop-in Hopper performance for standard server chassis.
Market range
$28,000to$32,399
H100 SXM5
Hopper80GB / SXM5
Added October 11, 2026
80GB Hopper module for compatible HGX and DGX multi-GPU systems.
Market range
$29,000to$31,125
A100 PCIe
Ampere80GB / PCIe
The proven Ampere workhorse, abundant in the secondary channel.
Market range
$12,550to$18,879
A100 PCIe
Ampere40GB / PCIe
The 40GB Ampere workhorse, abundant and affordable in the secondary channel.
Market range
$7,800to$12,278
A100 SXM4
Ampere80GB / SXM4
80GB Ampere server module for compatible HGX and DGX systems.
Market range
$9,900to$10,000
L40S
Ada48GB / PCIe
Versatile Ada accelerator for inference and visual compute.
Market range
$6,750to$8,750
RTX 6000 Ada
Ada48GB / PCIe
Ada-generation workstation card with 48GB for rendering and inference.
Market range
$4,750to$7,359
A40
Ampere48GB / PCIe
Reliable 48GB Ampere card for general-purpose acceleration.
Market range
$3,125to$4,899
L4
Ada24GB / PCIe
Low-power Ada card built for high-density, energy-efficient inference.
Market range
$3,120to$3,999
RTX A6000
Ampere48GB / PCIe
Ampere workstation card with 48GB for rendering and inference.
Market range
$3,500to$3,962
RTX 4090
Ada24GB / PCIe
Flagship Ada consumer card, popular for development and small-scale training.
Market range
$2,252to$3,050
A30
Ampere24GB / PCIe
Compact Ampere accelerator for cost-sensitive inference workloads.
Market range
$1,800to$2,799
RTX 3090
Ampere24GB / PCIe
Previous-gen consumer flagship, a budget entry into 24GB compute.
Market range
$908to$1,050
This grid covers 15 models. The monthly market-intelligence issue prices a few more as new SKUs enter our read; the numbers are the same in both, and the issue is where a SKU appears first. Read the current issue.
Informational only. Observed secondary-market estimates, not quotes, offers, or advice. Do not rely on these figures as the sole basis for a purchase.
What drives GPU pricing
Six factors set the number. We weigh all of them against the observation set behind this read.
Model & Generation
Hopper commands a premium over Ampere; architecture sets the floor.
Memory Configuration
More on-card memory widens the workloads a buyer can run, and the price.
Form Factor
SXM, PCIe, and NVL carry different interconnect value and chassis fit.
Condition
New, refurbished, and used each price differently against documented provenance.
Quantity
Volume moves the number in both directions depending on supply depth.
Warranty & Documentation
Testing records, certifications, and warranty coverage de-risk and lift value.
Need a number you can trust?
Tell us what you need or what you have. We handle the rest, from first conversation to final payment.