T4 vs V100
The T4 delivers 1.9× the FP16 compute of the T4 while costing 10.1× less on average, making it 423% more cost-efficient per TFLOP.
Spec Comparison
Spec
T4
V100
Architecture
Older
Older
VRAM
16 GB
32 GB
FP16 TFLOPS
65
125
Memory Bandwidth
320 GB/s
900 GB/s
MSRP
N/A
N/A
Used/Market Price
$1,500
$2,000
Live Pricing
Cost Efficiency
Metric
T4
V100
$/TFLOP/hr
$0.0140
$0.0731
$/GB-VRAM/hr
$0.0568
$0.2855
Lower $/TFLOP and $/GB-VRAM is better. Based on median hourly pricing.
Provider Availability
Only on T4 (5)
Only on V100 (6)
T4 Cloud Pricing
1557 instances| Provider | GPUs | VRAM | Region | Type | Price/hr | |
|---|---|---|---|---|---|---|
| CHEAPESTAzure | 1x | 16 GB | Asia-Pacific | Spot | $0.0684 | Rent |
| Azure | 1x | 16 GB | US-Central | Spot | $0.0686 | Rent |
| Azure | 1x | 16 GB | Asia-Pacific | Spot | $0.0977 | Rent |
| Azure | 1x | 16 GB | US-Central | Spot | $0.0980 | Rent |
| GCP | 1x | 16 GB | me-west1-b | Spot | $0.112 | Rent |
| GCP | 1x | 16 GB | me-west1-c | Spot | $0.112 | Rent |
| GCP | 1x | 16 GB | EU-West | Spot | $0.117 | Rent |
| GCP | 1x | 16 GB | me-west1-b | Spot | $0.118 | Rent |
| GCP | 1x | 16 GB | me-west1-c | Spot | $0.118 | Rent |
| AWS | 1x | 16 GB | South America | Spot | $0.123 | Rent |
V100 Cloud Pricing
527 instances| Provider | GPUs | VRAM | Region | Type | Price/hr | |
|---|---|---|---|---|---|---|
| CHEAPESTVast.ai | 1x | 16 GB | US-West | Spot | $0.0133 | Rent |
| Vast.ai | 1x | 16 GB | US-West | Spot | $0.0147 | Rent |
| Vast.ai | 2x | 32 GB | US-West | Spot | $0.0267 | Rent |
| Vast.ai | 2x | 32 GB | US-West | Spot | $0.0293 | Rent |
| Vast.ai | 1x | 16 GB | US-West | On-Demand | $0.0344 | Rent |
| Vast.ai | 1x | 16 GB | US-West | On-Demand | $0.0351 | Rent |
| Verda | 1x | 16 GB | EU-Central | Spot | $0.0483 | Rent |
| Vast.ai | 4x | 64 GB | US-West | Spot | $0.0533 | Rent |
| Vast.ai | 2x | 32 GB | US-West | On-Demand | $0.0702 | Rent |
| Vast.ai | 2x | 32 GB | US-West | On-Demand | $0.0722 | Rent |