Accelerators pricing
AWS Inferentia prices in ap-southeast-1 (Asia Pacific (Singapore))
Updated 2026-10-19
inf1.xlarge $0.308/h, inf1.2xlarge $0.489/h, inf1.6xlarge $1.59/h, inf1.24xlarge $6.38/h, inf2.xlarge $1.06/h, inf2.8xlarge $2.75/h, inf2.48xlarge $18.17/h.
Sizes
| Instance | Accelerators | Accel. memory | On-demand $/h | $/chip-hr | 3-yr RI no upfront $/h | Hours per $25k |
|---|---|---|---|---|---|---|
| inf1.xlarge | Inferentia ×1 | n/a | $0.308 | $0.308 | $0.167 | 81,169 h |
| inf1.2xlarge | Inferentia ×1 | n/a | $0.489 | $0.489 | $0.265 | 51,125 h |
| inf1.6xlarge | Inferentia ×4 | n/a | $1.59 | $0.3985 | $0.863 | 15,684 h |
| inf1.24xlarge | Inferentia ×16 | n/a | $6.38 | $0.3985 | $3.45 | 3,921 h |
| inf2.xlarge | Inferentia2 ×1 | 32 GB | $1.06 | $1.06 | $0.4586 | 23,552 h |
| inf2.8xlarge | Inferentia2 ×1 | 32 GB | $2.75 | $2.75 | $1.19 | 9,074 h |
| inf2.48xlarge | Inferentia2 ×12 | 384 GB | $18.17 | $1.51 | $7.85 | 1,376 h |
GPU instances in ap-southeast-1 for comparison
| Instance | Accelerators | Accel. memory | On-demand $/h | $/chip-hr | 3-yr RI no upfront $/h | Hours per $25k |
|---|---|---|---|---|---|---|
| g4dn.xlarge | NVIDIA T4 Tensor Core ×1 | 16 GB | $0.736 | $0.736 | $0.358 | 33,967 h |
| p4d.24xlarge | NVIDIA A100 ×8 | 320 GB | $26.35 | $3.29 | $11.25 | 949 h |
Other regions
Related cost calculators
- EC2 Pricing Calculator · Compare Instance Types & Costs
- Amazon SageMaker AI Pricing Calculator · On-Demand Studio, Training & Inference
Prices and credit amounts are estimates and may change. Check AWS for current terms.