Accelerators pricing
AWS Inferentia prices in ap-southeast-2 (Asia Pacific (Sydney))
Updated 2026-10-19
inf1.xlarge $0.285/h, inf1.2xlarge $0.453/h, inf1.6xlarge $1.48/h, inf1.24xlarge $5.90/h, inf2.xlarge $0.9857/h, inf2.8xlarge $2.56/h, inf2.48xlarge $16.88/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 | $0.285 | $0.285 | $0.137 | 87,719 h |
| inf1.2xlarge | Inferentia ×1 | n/a | $0.453 | $0.453 | $0.217 | 55,188 h |
| inf1.6xlarge | Inferentia ×4 | n/a | $1.48 | $0.3688 | $0.709 | 16,949 h |
| inf1.24xlarge | Inferentia ×16 | n/a | $5.90 | $0.3689 | $2.84 | 4,236 h |
| inf2.xlarge | Inferentia2 ×1 | 32 GB | $0.9857 | $0.9857 | $0.4258 | 25,364 h |
| inf2.8xlarge | Inferentia2 ×1 | 32 GB | $2.56 | $2.56 | $1.11 | 9,772 h |
| inf2.48xlarge | Inferentia2 ×12 | 384 GB | $16.88 | $1.41 | $7.29 | 1,481 h |
GPU instances in ap-southeast-2 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 | $0.684 | $0.684 | $0.332 | 36,550 h |
| g5.xlarge | NVIDIA A10G ×1 | 24 GB | $1.31 | $1.31 | $0.5651 | 19,113 h |
| g6.xlarge | NVIDIA L4 ×1 | 24 GB | $1.05 | $1.05 | $0.4803 | 23,891 h |
| p4d.24xlarge | NVIDIA A100 ×8 | 320 GB | $28.54 | $3.57 | $12.19 | 876 h |
| p5.48xlarge | NVIDIA H100 ×8 | 640 GB | $71.55 | $8.94 | $30.91 | 349 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.