AWS batch inference GPU prices
Batch inference can use cheaper and less stable pricing modes when queues are flexible and retries are acceptable. The cheapest tracked AWS row in this slice is A100 SXM4 at $3.09/hr.
Current AWS rows for batch inference
AWS has 4 qualifying GPU models across 4 current price rows for this workload. The overall tracked market floor is $0.13/hr on GCP L40, making AWS $2.96/hr above that floor.
| GPU | VRAM | Type | Median hourly | Monthly | Offers | Updated |
|---|---|---|---|---|---|---|
|
A100 SXM4
High Performance
|
80GB HBM2e | on-demand | $3.09/hr | $2,254/mo | 4 | Jun 21, 2026 |
|
L40
Mid-Range
|
48GB GDDR6 | on-demand | $3.39/hr | $2,471/mo | 16 | Jun 21, 2026 |
|
H100 SXM
Flagship
|
80GB HBM3 | on-demand | $6.88/hr | $5,022/mo | 2 | Jun 21, 2026 |
|
H200
Flagship
|
141GB HBM3e | on-demand | $7.91/hr | $5,776/mo | 2 | Jun 21, 2026 |
AWS batch inference pricing overview
This page narrows AWS's GPU catalog to the rows most likely to matter for batch inference. It is built for buyers who already know the provider they are evaluating and need a workload-specific price shortlist.
Offline inference queues, embedding jobs, catch-up workloads, and cost-sensitive internal processing. Use the table below to move from the cheapest visible row into adjacent provider/GPU pages, broader guides, and market-floor comparisons.
Cheapest AWS row for batch inference
AWS currently starts at $3.09/hr for batch inference with A100 SXM4 on on-demand pricing. The overall tracked market floor is $0.13/hr on GCP L40, making AWS $2.96/hr above that floor.
How this workload slice is computed
We filter the live compare payload to spot, community, and on-demand rows with at least 24GB of VRAM, then sort qualifying AWS rows by current median hourly price.
AWS batch inference pricing FAQ
What is the cheapest AWS option for batch inference?
AWS currently starts at $3.09/hr for batch inference with A100 SXM4 on on-demand pricing.
Is AWS cheapest for batch inference?
The overall tracked market floor is $0.13/hr on GCP L40, making AWS $2.96/hr above that floor.
What GPUs count toward this batch inference page?
This page filters to 24GB+ GPUs and uses spot, community, and on-demand pricing.
How fresh is this AWS batch inference page?
The rows are recalculated from the latest stored provider snapshot. The freshest qualifying row visible here is from Jun 21, 2026.
Next searches after AWS batch inference
These links move sideways into the full provider catalog, workload guide, market floor, and adjacent provider workload pages.