Accelerators pricing
AWS Inferentia prices in sa-east-1 (South America (Sao Paulo))
Updated 2026-10-19
inf1.xlarge $0.377/h, inf1.2xlarge $0.598/h, inf1.6xlarge $1.95/h, inf1.24xlarge $7.80/h, inf2.xlarge $1.29/h, inf2.8xlarge $3.35/h, inf2.48xlarge $22.07/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 | $0.377 | $0.377 | $0.181 | 66,313 h |
| inf1.2xlarge | Inferentia ×1 | n/a | $0.598 | $0.598 | $0.287 | 41,806 h |
| inf1.6xlarge | Inferentia ×4 | n/a | $1.95 | $0.4875 | $0.937 | 12,821 h |
| inf1.24xlarge | Inferentia ×16 | n/a | $7.80 | $0.4875 | $3.75 | 3,205 h |
| inf2.xlarge | Inferentia2 ×1 | 32 GB | $1.29 | $1.29 | $0.5568 | 19,396 h |
| inf2.8xlarge | Inferentia2 ×1 | 32 GB | $3.35 | $3.35 | $1.45 | 7,473 h |
| inf2.48xlarge | Inferentia2 ×12 | 384 GB | $22.07 | $1.84 | $9.53 | 1,133 h |
GPU instances in sa-east-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 | $0.894 | $0.894 | $0.454 | 27,964 h |
| g5.xlarge | NVIDIA A10G ×1 | 24 GB | $1.71 | $1.71 | $0.7387 | 14,620 h |
| g6.xlarge | NVIDIA L4 ×1 | 24 GB | $1.37 | $1.37 | $0.6279 | 18,275 h |
| p4d.24xlarge | NVIDIA A100 ×8 | 320 GB | $35.56 | $4.44 | $15.05 | 703 h |
| p5.48xlarge | NVIDIA H100 ×8 | 640 GB | $92.47 | $11.56 | $39.95 | 270 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.