← GPU cloud (on-demand)
Nebius
Nebius L40S (Intel CPU)
Inference-class L40S, 'from' price with Intel CPU (AMD CPU variant from $1.82).
USD per GPU-hour
$1.55
Verified Oct 6, 2026
#2 cheapest of 20 in GPU cloud (on-demand)
Official pricing ↗Capabilities, explained
What this API can do, and what each capability means for your project.
GPU
L40S
The GPU model. Newer generations are faster per dollar for large models.
VRAM
48 GB
Memory per GPU. A 70B-parameter model needs ~140 GB in 16-bit, or ~40 GB quantised.
Interconnect
none
How fast GPUs talk to each other; matters for multi-GPU training.
Regions
—
Where the hardware is located (latency, data residency).
Per-second billing
—
You pay only for the seconds used rather than full hours.
Price history
Only one price recorded so far. The chart appears once the price changes.