Accelerators pricing
AWS Inferentia prices in eu-west-1 (EU (Ireland))
Updated 2026-10-19
inf1.xlarge $0.254/h, inf1.2xlarge $0.403/h, inf1.6xlarge $1.31/h, inf1.24xlarge $5.26/h, inf2.xlarge $0.9477/h, inf2.8xlarge $2.46/h, inf2.48xlarge $16.23/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 | $0.254 | $0.254 | $0.122 | 98,425 h |
| inf1.2xlarge | Inferentia ×1 | n/a | $0.403 | $0.403 | $0.194 | 62,035 h |
| inf1.6xlarge | Inferentia ×4 | n/a | $1.31 | $0.3287 | $0.632 | 19,011 h |
| inf1.24xlarge | Inferentia ×16 | n/a | $5.26 | $0.3287 | $2.53 | 4,753 h |
| inf2.xlarge | Inferentia2 ×1 | 32 GB | $0.9477 | $0.9477 | $0.4094 | 26,378 h |
| inf2.8xlarge | Inferentia2 ×1 | 32 GB | $2.46 | $2.46 | $1.06 | 10,163 h |
| inf2.48xlarge | Inferentia2 ×12 | 384 GB | $16.23 | $1.35 | $7.01 | 1,541 h |
GPU instances in eu-west-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 | $0.587 | $0.587 | $0.253 | 42,589 h |
| g5.xlarge | NVIDIA A10G ×1 | 24 GB | $1.12 | $1.12 | $0.4851 | 22,262 h |
| p4d.24xlarge | NVIDIA A100 ×8 | 320 GB | $23.72 | $2.96 | $10.15 | 1,054 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.