Accelerators pricing
AWS Inferentia prices in eu-west-2 (EU (London))
Updated 2026-10-19
inf1.xlarge $0.267/h, inf1.2xlarge $0.424/h, inf1.6xlarge $1.38/h, inf1.24xlarge $5.53/h, inf2.xlarge $1.14/h, inf2.8xlarge $2.95/h, inf2.48xlarge $19.47/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 | $0.267 | $0.267 | $0.128 | 93,633 h |
| inf1.2xlarge | Inferentia ×1 | n/a | $0.424 | $0.424 | $0.204 | 58,962 h |
| inf1.6xlarge | Inferentia ×4 | n/a | $1.38 | $0.3455 | $0.664 | 18,090 h |
| inf1.24xlarge | Inferentia ×16 | n/a | $5.53 | $0.3456 | $2.66 | 4,521 h |
| inf2.xlarge | Inferentia2 ×1 | 32 GB | $1.14 | $1.14 | $0.5241 | 21,982 h |
| inf2.8xlarge | Inferentia2 ×1 | 32 GB | $2.95 | $2.95 | $1.36 | 8,469 h |
| inf2.48xlarge | Inferentia2 ×12 | 384 GB | $19.47 | $1.62 | $8.97 | 1,284 h |
GPU instances in eu-west-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 | $0.615 | $0.615 | $0.299 | 40,650 h |
| g5.xlarge | NVIDIA A10G ×1 | 24 GB | $1.28 | $1.28 | $0.5517 | 19,577 h |
| g6.xlarge | NVIDIA L4 ×1 | 24 GB | $1.02 | $1.02 | $0.4689 | 24,471 h |
| p4d.24xlarge | NVIDIA A100 ×8 | 320 GB | $28.54 | $3.57 | n/a | 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.