Accelerators pricing
AWS Inferentia prices in eu-north-1 (EU (Stockholm))
Updated 2026-10-19
inf1.xlarge $0.242/h, inf1.2xlarge $0.385/h, inf1.6xlarge $1.25/h, inf1.24xlarge $5.02/h, inf2.xlarge $0.834/h, inf2.8xlarge $2.16/h, inf2.48xlarge $14.28/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 | $0.242 | $0.242 | $0.117 | 103,306 h |
| inf1.2xlarge | Inferentia ×1 | n/a | $0.385 | $0.385 | $0.185 | 64,935 h |
| inf1.6xlarge | Inferentia ×4 | n/a | $1.25 | $0.3135 | $0.603 | 19,936 h |
| inf1.24xlarge | Inferentia ×16 | n/a | $5.02 | $0.3135 | $2.41 | 4,984 h |
| inf2.xlarge | Inferentia2 ×1 | 32 GB | $0.834 | $0.834 | $0.3603 | 29,975 h |
| inf2.8xlarge | Inferentia2 ×1 | 32 GB | $2.16 | $2.16 | $0.9351 | 11,549 h |
| inf2.48xlarge | Inferentia2 ×12 | 384 GB | $14.28 | $1.19 | $6.17 | 1,751 h |
GPU instances in eu-north-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 | $0.558 | $0.558 | $0.241 | 44,803 h |
| g5.xlarge | NVIDIA A10G ×1 | 24 GB | $1.07 | $1.07 | $0.4609 | 23,430 h |
| g6.xlarge | NVIDIA L4 ×1 | 24 GB | $0.8536 | $0.8536 | $0.3918 | 29,288 h |
| p4d.24xlarge | NVIDIA A100 ×8 | 320 GB | $23.72 | $2.96 | n/a | 1,054 h |
| p5.48xlarge | NVIDIA H100 ×8 | 640 GB | $58.89 | $7.36 | $25.44 | 425 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.