Accelerators pricing
AWS Inferentia pricing
Updated 2026-10-19
7 instance sizes, offered in 14 of 14 tracked regions.
Sizes (us-east-1)
| Instance | Accelerators | Accel. memory | On-demand $/h | $/chip-hr | 3-yr RI no upfront $/h | Hours per $25k |
|---|---|---|---|---|---|---|
| inf1.xlarge | Inferentia ×1 | n/a | $0.228 | $0.228 | $0.11 | 109,649 h |
| inf1.2xlarge | Inferentia ×1 | n/a | $0.362 | $0.362 | $0.174 | 69,061 h |
| inf1.6xlarge | Inferentia ×4 | n/a | $1.18 | $0.295 | $0.567 | 21,186 h |
| inf1.24xlarge | Inferentia ×16 | n/a | $4.72 | $0.2951 | $2.27 | 5,295 h |
| inf2.xlarge | Inferentia2 ×1 | 32 GB | $0.7582 | $0.7582 | $0.3275 | 32,973 h |
| inf2.8xlarge | Inferentia2 ×1 | 32 GB | $1.97 | $1.97 | $0.8501 | 12,704 h |
| inf2.48xlarge | Inferentia2 ×12 | 384 GB | $12.98 | $1.08 | $5.61 | 1,926 h |
Regions
| Region | Sizes offered | Cheapest $/h |
|---|---|---|
| us-east-1 | 7 | $0.228 |
| us-east-2 | 7 | $0.228 |
| us-west-2 | 7 | $0.228 |
| eu-central-1 | 7 | $0.285 |
| eu-west-1 | 7 | $0.254 |
| eu-west-2 | 7 | $0.267 |
| eu-north-1 | 7 | $0.242 |
| ap-south-1 | 7 | $0.24 |
| ap-southeast-1 | 7 | $0.308 |
| ap-southeast-2 | 7 | $0.285 |
| ap-northeast-1 | 7 | $0.308 |
| ca-central-1 | 4 | $0.254 |
| sa-east-1 | 7 | $0.377 |
| af-south-1 | 2 | $0.302 |
Single-accelerator inference: inf2.xlarge vs GPU instances (us-east-1)
inf2.xlarge gives 32,973 hours per $25k vs g5.xlarge 24,851 h (credits last +33% longer on inf2.xlarge), g6.xlarge 31,064 h (credits last +6% longer on inf2.xlarge), g4dn.xlarge 47,529 h (credits last -31% longer on inf2.xlarge)
| Instance | Accelerators | Accel. memory | On-demand $/h | $/chip-hr | 3-yr RI no upfront $/h | Hours per $25k |
|---|---|---|---|---|---|---|
| inf2.xlarge | Inferentia2 ×1 | 32 GB | $0.7582 | $0.7582 | $0.3275 | 32,973 h |
| g5.xlarge | NVIDIA A10G ×1 | 24 GB | $1.01 | $1.01 | $0.4346 | 24,851 h |
| g6.xlarge | NVIDIA L4 ×1 | 24 GB | $0.8048 | $0.8048 | $0.3694 | 31,064 h |
| g4dn.xlarge | NVIDIA T4 Tensor Core ×1 | 16 GB | $0.526 | $0.526 | $0.227 | 47,529 h |
Hours per $25k = how long credits last at the on-demand price. Throughput per hour differs by model and needs the AWS Neuron SDK; benchmark before switching.
Large-model inference: inf2.48xlarge vs GPU instances (us-east-1)
inf2.48xlarge gives 1,926 hours per $25k vs g5.48xlarge 1,535 h (credits last +25% longer on inf2.48xlarge), g6e.12xlarge 2,383 h (credits last -19% longer on inf2.48xlarge)
| Instance | Accelerators | Accel. memory | On-demand $/h | $/chip-hr | 3-yr RI no upfront $/h | Hours per $25k |
|---|---|---|---|---|---|---|
| inf2.48xlarge | Inferentia2 ×12 | 384 GB | $12.98 | $1.08 | $5.61 | 1,926 h |
| g5.48xlarge | NVIDIA A10G ×8 | 192 GB | $16.29 | $2.04 | $7.04 | 1,535 h |
| g6e.12xlarge | NVIDIA L40S ×4 | 192 GB | $10.49 | $2.62 | $4.53 | 2,383 h |
Hours per $25k = how long credits last at the on-demand price. Throughput per hour differs by model and needs the AWS Neuron SDK; benchmark before switching.
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.