inf1.24xlargeAWS Pricing, Specs & Benchmarks

The inf1 family is a generation-1 AWS Inferentia ML inference line running on Intel Xeon (x86_64). inf1.24xlarge provides 96 vCPUs and 192GB of RAM (a 1:2 vCPU-to-memory ratio), priced at $4.7210/hr On-Demand — about $3399.12 per month at 24×7 utilization.

AWS Inferentia ML inference instances are sized for large-batch ML inference, particularly for transformer-based language and vision models that have been compiled with the Neuron SDK. If your workload doesn't match that profile — for example, if you're running a memory-bound app on a compute-optimized instance, or a CPU-pegged batch job on a burstable t-series — you'll likely pay for capacity you can't use or run into bottlenecks you didn't anticipate. The pages for sibling families (linked further down) cover those alternatives in detail.

In the AWS instance-naming convention, the digit after the series letter is the generation — higher is newer. AWS's current-generation alternative in the same series is **inf2**, which generally offers better price/performance on newer silicon; if you're spinning up a new workload it's usually worth comparing the two before committing.

Pricing varies by region (sometimes meaningfully — the gap between the cheapest and most expensive AWS region for the same SKU is often 15–30%). The regional pricing table further down shows where inf1.24xlarge is cheapest today, both On-Demand and Spot. Spot pricing for inf1.24xlarge is currently $0.9298/hr — roughly 80% off On-Demand — which makes the instance viable for fault-tolerant batch jobs, CI fleets, and any workload that can tolerate interruption with short notice.