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 ($)
Asia Pacific (Hyderabad) / ap-south-2
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 Instances3614403.6720
ml.c5.2xlargeStandard Instances41600.4080
ml.c5.4xlargeStandard Instances83200.8160
ml.c5.9xlargeStandard Instances187201.8360
ml.c5.largeStandard Instances1400.1020
ml.c5.xlargeStandard Instances2800.2040
ml.c5d.18xlargeCompute Optimized Instances3614404.2770-3%
ml.c5d.2xlargeCompute Optimized Instances41600.4750-2%
ml.c5d.4xlargeCompute Optimized Instances83200.9500-2%
ml.c5d.9xlargeCompute Optimized Instances187202.1380-2%
ml.c5d.largeCompute Optimized Instances1400.1190-3%
ml.c5d.xlargeCompute Optimized Instances2800.2380-3%
ml.m5.12xlargeStandard Instances2419202.9090-4%
ml.m5.24xlargeStandard Instances4838405.8180-4%
ml.m5.2xlargeStandard Instances43200.4850-4%
ml.m5.4xlargeStandard Instances86400.9700-4%
ml.m5.largeStandard Instances1800.1210-4%
ml.m5.xlargeStandard Instances21600.2420-4%
ml.m5d.12xlargeStandard Instances2419203.5140-7%
ml.m5d.24xlargeStandard Instances4838407.0270-7%
ml.m5d.2xlargeStandard Instances43200.5860-7%
ml.m5d.4xlargeStandard Instances86401.1710-7%
ml.m5d.largeStandard Instances1800.1460-6%
ml.m5d.xlargeStandard Instances21600.2930-7%
ml.r5.12xlargeStandard Instances2438403.7440-3%
ml.r5.24xlargeStandard Instances4876807.4880-3%
ml.r5.4xlargeStandard Instances812801.2480-3%
ml.r5.largeStandard Instances11600.1560-4%
ml.r5.xlargeStandard Instances23200.3120-3%
ml.r5d.12xlargeMemory Optimized Instances2438404.3490-4%
ml.r5d.24xlargeMemory Optimized Instances4876808.6980-4%
ml.r5d.2xlargeMemory Optimized Instances46400.7250-4%
ml.r5d.4xlargeMemory Optimized Instances812801.4500-4%
ml.r5d.largeMemory Optimized Instances11600.1810-4%
ml.r5d.xlargeMemory Optimized Instances23200.3620-4%
ml.c6g.12xlargeCompute Optimized Instances489601.2270
ml.c6g.16xlargeCompute Optimized Instances6412801.6360
ml.c6g.2xlargeCompute Optimized Instances81600.2040
ml.c6g.4xlargeCompute Optimized Instances163200.4090
ml.c6g.8xlargeCompute Optimized Instances326400.8180
ml.c6g.largeCompute Optimized Instances2400.0510
ml.c6g.xlargeCompute Optimized Instances4800.1020
ml.m6g.12xlargeStandard Instances4819201.4570
ml.m6g.16xlargeStandard Instances6425601.9430
ml.m6g.2xlargeStandard Instances83200.2430
ml.m6g.4xlargeStandard Instances166400.4860
ml.m6g.8xlargeStandard Instances3212800.9720
ml.m6g.largeStandard Instances2800.0610
ml.m6g.xlargeStandard Instances41600.1210
ml.m6gd.12xlargeStandard Instances4819201.7400
ml.m6gd.16xlargeStandard Instances6425602.3190
ml.m6gd.2xlargeStandard Instances83200.2900
ml.m6gd.4xlargeStandard Instances166400.5800
ml.m6gd.8xlargeStandard Instances3212801.1600
ml.m6gd.largeStandard Instances2800.0720
ml.m6gd.xlargeStandard Instances41600.1450
ml.r6g.12xlargeStandard Instances4838401.8720
ml.r6g.16xlargeStandard Instances6451202.4960
ml.r6g.2xlargeStandard Instances86400.3120
ml.r6g.4xlargeStandard Instances1612800.6240
ml.r6g.8xlargeStandard Instances3225601.2480
ml.r6g.largeStandard Instances21600.0780
ml.r6g.xlargeStandard Instances43200.1560