Amazon SageMaker AI Instances Comparison

Batch Export API
Download complete pricing datasets

Discover and compare Amazon SageMaker machine learning instance specifications and pricing on a single page, covering various workload types and regions. Filter by GPU, inference accelerators, vCPUs, and memory. Compare prices across training, inference, and studio workloads.

The data is frequently updated from the AWS API, but may not be accurate. This site is not affiliated with Amazon or AWS. The latest update occurred on September 4, 2026 at 12:31 AM UTC

US Dollar ($)
Israel (Tel Aviv) / il-central-1
Per Hour
Real-Time Inference
On-Demand
vCPUs
to
Memory
to
Instance Type
Instance Family
vCPUs
Memory (GiB)
GPUs
Instance Price
Best Alternative Instances
Savings Options
Best Price Region / Diff
ml.c5.18xlargeStandard Instances3614404.3500-15%
ml.c5.2xlargeStandard Instances41600.4800-15%
ml.c5.4xlargeStandard Instances83200.9700-15%
ml.c5.9xlargeStandard Instances187202.1800-15%
ml.c5.largeStandard Instances1400.1200-15%
ml.c5.xlargeStandard Instances2800.2400-15%
ml.c5d.18xlargeCompute Optimized Instances3614404.9400-16%
ml.c5d.2xlargeCompute Optimized Instances41600.5500-16%
ml.c5d.4xlargeCompute Optimized Instances83201.1000-16%
ml.c5d.9xlargeCompute Optimized Instances187202.4700-16%
ml.c5d.largeCompute Optimized Instances1400.1400-17%
ml.c5d.xlargeCompute Optimized Instances2800.2700-14%
ml.g5.12xlargeAccelerated Computing Instances2419248.3100-14%
ml.g5.16xlargeAccelerated Computing Instances3225616.0000-14%
ml.g5.24xlargeAccelerated Computing Instances48384411.9300-14%
ml.g5.2xlargeAccelerated Computing Instances43211.7800-14%
ml.g5.48xlargeAccelerated Computing Instances96768823.8600-14%
ml.g5.4xlargeAccelerated Computing Instances86412.3800-14%
ml.g5.8xlargeAccelerated Computing Instances1612813.5900-14%
ml.g5.xlargeAccelerated Computing Instances21611.6500-16%
ml.m5.12xlargeStandard Instances2419203.2400-15%
ml.m5.24xlargeStandard Instances4838406.4700-15%
ml.m5.2xlargeStandard Instances43200.5400-15%
ml.m5.4xlargeStandard Instances86401.0800-15%
ml.m5.largeStandard Instances1800.1300-14%
ml.m5.xlargeStandard Instances21600.2700-15%
ml.m5d.12xlargeStandard Instances2419203.8100-14%
ml.m5d.24xlargeStandard Instances4838407.6200-14%
ml.m5d.2xlargeStandard Instances43200.6300-14%
ml.m5d.4xlargeStandard Instances86401.2700-14%
ml.m5d.largeStandard Instances1800.1600-14%
ml.m5d.xlargeStandard Instances21600.3200-14%
ml.r5.12xlargeStandard Instances2438404.2600-14%
ml.r5.24xlargeStandard Instances4876808.5300-14%
ml.r5.4xlargeStandard Instances812801.4200-14%
ml.r5.largeStandard Instances11600.1800-15%
ml.r5.xlargeStandard Instances23200.3600-15%
ml.r5d.12xlargeMemory Optimized Instances2438404.8400-14%
ml.r5d.24xlargeMemory Optimized Instances4876809.6800-14%
ml.r5d.2xlargeMemory Optimized Instances46400.8100-14%
ml.r5d.4xlargeMemory Optimized Instances812801.6100-14%
ml.r5d.largeMemory Optimized Instances11600.2000-13%
ml.r5d.xlargeMemory Optimized Instances23200.4000-13%
ml.c6g.12xlargeCompute Optimized Instances489602.2100-44%
ml.c6g.16xlargeCompute Optimized Instances6412802.9400-44%
ml.c6g.2xlargeCompute Optimized Instances81600.3700-44%
ml.c6g.4xlargeCompute Optimized Instances163200.7400-44%
ml.c6g.8xlargeCompute Optimized Instances326401.4700-44%
ml.c6g.largeCompute Optimized Instances2400.0900-43%
ml.c6g.xlargeCompute Optimized Instances4800.1800-43%
ml.c6gn.16xlargeCompute Optimized Instances6412803.9400-17%
ml.c6gn.2xlargeCompute Optimized Instances81600.4900-17%
ml.c6gn.4xlargeCompute Optimized Instances163200.9800-17%
ml.c6gn.8xlargeCompute Optimized Instances326401.9700-17%
ml.c6gn.largeCompute Optimized Instances2400.1200-15%
ml.c6gn.xlargeCompute Optimized Instances4800.2500-19%
ml.c6i.12xlargeCompute Optimized Instances249602.7600-13%
ml.c6i.16xlargeCompute Optimized Instances3212803.6800-13%
ml.c6i.24xlargeCompute Optimized Instances4819205.5200-13%
ml.c6i.2xlargeCompute Optimized Instances41600.4600-13%
ml.c6i.32xlargeCompute Optimized Instances6425607.3500-12%
ml.c6i.4xlargeCompute Optimized Instances83200.9200-13%
ml.c6i.8xlargeCompute Optimized Instances166401.8400-13%
ml.c6i.largeCompute Optimized Instances1400.1100-12%
ml.c6i.xlargeCompute Optimized Instances2800.2300-13%
ml.m6g.12xlargeStandard Instances4819202.6000-43%
ml.m6g.16xlargeStandard Instances6425603.4700-44%
ml.m6g.2xlargeStandard Instances83200.4300-43%
ml.m6g.4xlargeStandard Instances166400.8700-44%
ml.m6g.8xlargeStandard Instances3212801.7300-43%
ml.m6g.largeStandard Instances2800.1100-44%
ml.m6g.xlargeStandard Instances41600.2200-45%
ml.m6gd.12xlargeStandard Instances4819203.0500-42%
ml.m6gd.16xlargeStandard Instances6425604.0600-42%
ml.m6gd.2xlargeStandard Instances83200.5100-43%
ml.m6gd.4xlargeStandard Instances166401.0200-43%
ml.m6gd.8xlargeStandard Instances3212802.0300-42%
ml.m6gd.largeStandard Instances2800.1300-44%
ml.m6gd.xlargeStandard Instances41600.2500-42%
ml.r6g.12xlargeStandard Instances4838403.4100-45%
ml.r6g.16xlargeStandard Instances6451204.5500-45%
ml.r6g.2xlargeStandard Instances86400.5700-45%
ml.r6g.4xlargeStandard Instances1612801.1400-45%
ml.r6g.8xlargeStandard Instances3225602.2700-45%
ml.r6g.largeStandard Instances21600.1400-44%
ml.r6g.xlargeStandard Instances43200.2800-44%