Nvidia logo

A100 vs L40S

The A100 features 80GB HBM2e for training, while the L40S offers 48GB GDDR6 for inference. Choose A100 for training workloads, L40S for inference workloads.

Overview

Nvidia logo Nvidia A100 Nvidia logo Nvidia L40S
Summary Previous-gen data center workhorse for AI training and inference. Cost-effective data center GPU for AI inference and media workloads.
Architecture Ampere Ada Lovelace
Memory 40GB / 80GB HBM2e 48GB GDDR6
Memory Bandwidth 1,935 GB/s 864 GB/s
Performance 312 TFLOPS (FP16) 362 TFLOPS (FP16)
Release Date Q2 2020 Q3 2023
Performance Segment High Performance High Performance
Datasheet Link Link

Price comparison

How we rank providers

Default ranking

Each provider appears once per GPU, ranked on three things in order:

  1. Availability: in stock, then unconfirmed, then waitlist, then out of stock. A price you can act on outranks a cheaper one you cannot.
  2. Billing type: on-demand rates rank ahead of spot and reserved ones. A spot rate is cheaper because it can be reclaimed, and a reserved rate because it is a commitment.
  3. Price: the lowest hourly price a provider charges for a single one of that GPU, with other currencies converted to USD first.

Providers that tie on price are sorted alphabetically.

Reserved rates are not separated by term length, so a multi-year commitment can rank above a one-month one. The term is shown beneath each price.

Transparency and funding

Ads and sponsors: Any paid placements are fixed at the top and labeled as sponsored content.

Affiliates: Any affiliate links will be indicated to you as well. We may earn a commission if you click them, but this never influences the ranking order.

Nvidia A100 logo A100 Pricing

There is a 97% difference between the highest and lowest listings for the A100. You can pay up to $5.04/hr, but the market floor is currently $0.13/hr per GPU (spot instance).

Nvidia L40S logo L40S Pricing

Listings for the L40S reach $7.58/hr, often reflecting a premium for high availability. However, you might be able to find available instances from as low as $0.33/hr per GPU (spot instance).

Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.

Alternative GPUs

Here's how these GPUs compare against alternatives:

View all GPUs

Our data for Nvidia A100 was last updated on Aug. 18, 2026, and for Nvidia L40S on March 25, 2026.

Packet·ai Logo
Packet·ai
Our sponsor
B200 @ $3.75/h on demand
No contract, no spot interrupts, no cluster minimums
Full root SSH, web dashboard, CI/CD ready
Reserve Now