Skip to main content

A100 vs T4

The A100 delivers 4.8× the FP16 compute of the T4 while costing 9.1× more on average, making the T4 90% more cost-efficient per TFLOP.

Spec Comparison

Spec
A100
T4
Architecture
Ampere
Older
VRAM
80 GB
16 GB
FP16 TFLOPS
312
65
Memory Bandwidth
2,000 GB/s
320 GB/s
MSRP
$10,000
N/A
Used/Market Price
$7,000
$1,500

Live Pricing

A100
Cheapest
$0.0800/hr
Median
$8.30/hr
Average
$13/hr
Providers
14
Instances
363
T4
Cheapest
$0.0684/hr
Median
$0.909/hr
Average
$1.53/hr
Providers
8
Instances
1557

Cost Efficiency

Metric
A100
T4
$/TFLOP/hr
$0.0266
$0.0140
$/GB-VRAM/hr
$0.1038
$0.0568

Lower $/TFLOP and $/GB-VRAM is better. Based on median hourly pricing.

Provider Availability

A100 Cloud Pricing

363 instances
ProviderGPUsVRAMRegionTypePrice/hr
CHEAPESTVast.ai1x40 GBEU-CentralSpot$0.0800Rent
Vast.ai1x40 GBEU-CentralOn-Demand$0.0934Rent
Vultr1x4 GBewrOn-Demand$0.123Rent
Vultr1x4 GBfraOn-Demand$0.123Rent
Vultr1x4 GBsjcOn-Demand$0.123Rent
Vultr1x4 GBnrtOn-Demand$0.123Rent
Vultr1x8 GBewrOn-Demand$0.247Rent
Vultr1x8 GBnrtOn-Demand$0.247Rent
Vultr1x8 GBblrOn-Demand$0.247Rent
Verda1x40 GBEU-CentralSpot$0.252Rent

T4 Cloud Pricing

1557 instances
ProviderGPUsVRAMRegionTypePrice/hr
CHEAPESTAzure1x16 GBAsia-PacificSpot$0.0684Rent
Azure1x16 GBUS-CentralSpot$0.0686Rent
Azure1x16 GBAsia-PacificSpot$0.0977Rent
Azure1x16 GBUS-CentralSpot$0.0980Rent
GCP1x16 GBme-west1-bSpot$0.112Rent
GCP1x16 GBme-west1-cSpot$0.112Rent
GCP1x16 GBEU-WestSpot$0.117Rent
GCP1x16 GBme-west1-bSpot$0.118Rent
GCP1x16 GBme-west1-cSpot$0.118Rent
AWS1x16 GBSouth AmericaSpot$0.123Rent

Compare with Other GPUs