The NVIDIA T4 is an enterprise-class GPU built on the Turing architecture, featuring 16 GB of memory with 300 GB/s of memory bandwidth and a 70 W TDP. It delivers 8.1 TFLOPS of FP32 performance and 65 TFLOPS of FP16 tensor performance. Currently available from 2 providers starting at $0.20/GPU/hour, with a market median of $6.10/GPU/hour across 4 configurations.
Cheapest
$0.200/hr
Theta EdgeCloud
Median
$6.100/hr
across 4 offerings
Most expensive
$12.000/hr
Vast.ai
90-day trend
+2950.0%
median rate
Hardware specifications
Same across all providers
Memory
16 GB
FP16 performance
65 TFLOPS
peak
TDP
70 W
Memory bandwidth
300 GB/s
Architecture
Turing
FP32 performance
8.1 TFLOPS
Brand
NVIDIA
Series
T4
Market price history
Median price across all providers
2 offerings from 2 providers
Sorted by price ascending. Compare configurations side-by-side.
| Provider | Count | vCPU | RAM | Region | Per GPU hour | Total/hr | Action |
|---|---|---|---|---|---|---|---|
 Theta EdgeCloudCheapest | ×1 | 2 | 8 GB | -- | $0.200 | From$0.20 | Launch |
 Vast.aiReferral link | ×1 | 1 | 2 GB |  | $12.000 +7900.0% 30d | From$12.00 | Launch |
See more GPUs like this in
Want more from this page?
See incorrect data?
Frequently asked questions
How much does the T4 cost per hour?
The T4 starts at $0.20 per GPU-hour, with a median of $6.10 across 4 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.
Which cloud providers offer the T4?
2 providers currently list the T4: Vast.ai, Theta EdgeCloud. Compare their hourly pricing, regions and machine specs in the table above.
How much VRAM does the T4 have?
The T4 comes with 16 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.
Where is the T4 cheapest?
The lowest on-demand price we currently track for the T4 is $0.20 per GPU-hour at Theta EdgeCloud. Because providers update pricing and availability frequently, check the live table above before you launch.