Provider workload page

GCP 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 GCP row in this slice is L40 at $0.13/hr.

24GB+ VRAM spot pricing community pricing on-demand pricing Updated Jun 21, 2026
Cheapest qualifying row
$0.13/hr
L40 ยท spot
Monthly estimate
$96/mo
730 hours at current median price
Qualifying GPUs
3
6 current rows updated Jun 21, 2026
Market gap
At floor
Floor is GCP L40

Current GCP rows for batch inference

GCP has 3 qualifying GPU models across 6 current price rows for this workload. GCP is currently at the tracked market floor for batch inference.

Updated Jun 21, 2026
GPU VRAM Type Median hourly Monthly Offers Updated
L40
Mid-Range
48GB GDDR6 spot $0.13/hr $96/mo 39 Jun 21, 2026
L40
Mid-Range
48GB GDDR6 on-demand $0.66/hr $482/mo 55 Jun 21, 2026
H100 SXM
Flagship
80GB HBM3 spot $2.51/hr $1,833/mo 49 Jun 21, 2026
B200
Flagship
192GB HBM3e spot $2.81/hr $2,051/mo 39 Jun 21, 2026
H100 SXM
Flagship
80GB HBM3 on-demand $4.84/hr $3,534/mo 178 Jun 21, 2026
B200
Flagship
192GB HBM3e on-demand $11.28/hr $8,232/mo 81 Jun 21, 2026

GCP batch inference pricing overview

This page narrows GCP'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 provider right now

Cheapest GCP row for batch inference

GCP currently starts at $0.13/hr for batch inference with L40 on spot pricing. GCP is currently at the tracked market floor for batch inference.

Methodology and freshness

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 GCP rows by current median hourly price.

GCP batch inference pricing FAQ

What is the cheapest GCP option for batch inference?

GCP currently starts at $0.13/hr for batch inference with L40 on spot pricing.

Is GCP cheapest for batch inference?

GCP is currently at the tracked market floor for batch inference.

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 GCP batch inference page?

The rows are recalculated from the latest stored provider snapshot. The freshest qualifying row visible here is from Jun 21, 2026.