Vast.ai 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 Vast.ai row in this slice is RTX 4090 at $0.40/hr.
Current Vast.ai rows for batch inference
Vast.ai has 12 qualifying GPU models across 12 current price rows for this workload. The overall tracked market floor is $0.13/hr on GCP L40, making Vast.ai $0.27/hr above that floor.
| GPU | VRAM | Type | Median hourly | Monthly | Offers | Updated |
|---|---|---|---|---|---|---|
|
RTX 4090
Budget
|
24GB GDDR6X | on-demand | $0.40/hr | $293/mo | 69 | Jun 21, 2026 |
|
L40
Mid-Range
|
48GB GDDR6 | on-demand | $0.45/hr | $331/mo | 1 | Jun 21, 2026 |
|
RTX 5090
Budget
|
32GB GDDR7 | on-demand | $0.53/hr | $390/mo | 129 | Jun 21, 2026 |
|
RTX 6000Ada
Mid-Range
|
48GB GDDR6 | on-demand | $0.60/hr | $439/mo | 8 | Jun 21, 2026 |
|
A100 PCIE
Mid-Range
|
80GB HBM2e | on-demand | $1.00/hr | $731/mo | 2 | Jun 19, 2026 |
|
A100 SXM4
High Performance
|
80GB HBM2e | on-demand | $1.14/hr | $834/mo | 6 | Jun 21, 2026 |
|
H100 PCIE
High Performance
|
80GB HBM3 | on-demand | $1.64/hr | $1,199/mo | 1 | Jun 21, 2026 |
|
H100 NVL
High Performance
|
94GB HBM3 | on-demand | $2.27/hr | $1,656/mo | 9 | Jun 21, 2026 |
|
H100 SXM
Flagship
|
80GB HBM3 | on-demand | $2.40/hr | $1,752/mo | 15 | Jun 21, 2026 |
|
H200 NVL
Flagship
|
141GB HBM3e | on-demand | $3.46/hr | $2,529/mo | 3 | Jun 21, 2026 |
Vast.ai batch inference pricing overview
This page narrows Vast.ai'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 Vast.ai row for batch inference
Vast.ai currently starts at $0.40/hr for batch inference with RTX 4090 on on-demand pricing. The overall tracked market floor is $0.13/hr on GCP L40, making Vast.ai $0.27/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 Vast.ai rows by current median hourly price.
Vast.ai batch inference pricing FAQ
What is the cheapest Vast.ai option for batch inference?
Vast.ai currently starts at $0.40/hr for batch inference with RTX 4090 on on-demand pricing.
Is Vast.ai cheapest for batch inference?
The overall tracked market floor is $0.13/hr on GCP L40, making Vast.ai $0.27/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 Vast.ai 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 Vast.ai batch inference
These links move sideways into the full provider catalog, workload guide, market floor, and adjacent provider workload pages.