T4
Efficient inference GPU with 16GB of GDDR6 memory. Optimized for AI inference at lower power consumption.
Average Price: $0.000178/s ($0.6398/h)
Available from 4 vendors
Serverless GPU Prices
Provider | GPU RAM | RAM | vCPUs | Price |
|---|---|---|---|---|
| Inferless | 2 | 3 | 0.5 | 0.000092/s 0.3312/h |
| Beam.cloud | 16 | 0.00015/s 0.54/h | ||
| Beam.cloud | 16 | 0.00015/s 0.54/h | ||
| Modal | 0.000164/s 0.5904/h | |||
| Modal | 0.000164/s 0.5904/h | |||
| Inferless | 16 | 20 | 3 | 0.000185/s 0.666/h |
| Inferless | 6 | 20 | 3 | 0.000185/s 0.666/h |
| Inferless | 1 | 2 | 3 | 0.00019/s 0.684/h |
| Replicate | 16 | 8 | 4 | 0.000225/s 0.81/h |
| Replicate | 16 | 16 | 4 | 0.000225/s 0.81/h |
| Replicate | 16 | 16 | 4 | 0.000225/s 0.81/h |