New B200 spot capacity is live in US East from $1.69 per GPU-hour. See availability
NVIDIA · Ada Lovelace · Data-center GPU

L40S from $0.15 per GPU-hour

Ada Lovelace in a data-center card: 48 GB, strong FP8 throughput and no NVLink. It is the value pick for inference servers and for generative image work, where memory bandwidth per dollar matters more than multi-GPU scaling.

Specifications from the vendor datasheet · prices updated recently

Price per GPU-hour 96 available
SpotReclaimed with 2 min notice · <5% over 30 days $0.15$0.0025 / min
On-demandRuns until you stop it $0.25−40% on spot
ReservedFixed rate, 1 to 12 months $0.15monthly term

Billed per started minute. 384 GB of GPU memory on a 8× node. Persistent storage $0.08 per GB-month. No egress fees.

GPU memory
48GBGDDR6
Bandwidth
864GB/sSets token throughput on inference
Node sizes
1× · 2× · 4× · 8×Same price per GPU at every size
Reclaim rate
<5%Spot instances reclaimed over 30 days
Node sizes

What you get with each L40S node.

All prices
Node GPU memory vCPU RAM Local NVMe Spot On-demand Action
1× L40S 48 GB 12 96 GB 1 TB $0.15/h $0.25/h Configure
2× L40S 96 GB 24 192 GB 2 TB $0.30/h $0.50/h Configure
4× L40S 192 GB 48 384 GB 4 TB $0.60/h $1.00/h Configure
8× L40S 384 GB 96 768 GB 8 TB $1.20/h $2.00/h Configure

GPU-to-GPU link: PCIe Gen4 x16 64 GB/s. Local NVMe is scratch space wiped when the instance ends; keep anything you need on a persistent disk.

Availability

96 L40S GPUs free right now.

Straight from the capacity pool the console books against. Prices are identical in every region — pick the one closest to your data.

US EastVirginia, US 40
Tier III100 Gbps per nodeus-east
US WestOregon, US 24
Tier III100 Gbps per nodeus-west
EU CentralFrankfurt, DE 32
Tier III100 Gbps per nodeeu-central

A region with zero free GPUs still accepts reserved capacity requests — we hold hardware for a term rather than sell what is already taken.

Memory planning

What fits in 48 GB — and what it costs per hour.

Weights need about 2 GB per billion parameters at FP16 / BF16, 1 GB per billion parameters at FP8, 0.5 GB per billion parameters at INT4. We keep 20% of the memory free for activations, the KV cache and the CUDA context, then take the smallest node that still fits.

Open model Parameters FP16 / BF16node · spot price FP8node · spot price INT4node · spot price
Mistral 7BAssistants, RAG, classification 7.2B $0.15/h $0.15/h $0.15/h
Llama 3.1 8BAssistants, agents, fine-tuning 8B $0.15/h $0.15/h $0.15/h
Gemma 2 27BHigher-quality assistants 27B $0.30/h $0.15/h $0.15/h
Qwen2.5 32BCode and reasoning 32B $0.30/h $0.15/h $0.15/h
Mixtral 8x7BMixture of experts, high throughput 46.7B $0.60/h $0.30/h $0.15/h
Llama 3.3 70BThe common production baseline 70B $0.60/h $0.30/h $0.15/h
Qwen2.5 72BMultilingual, long context 72B $0.60/h $0.30/h $0.15/h
Mixtral 8x22BMixture of experts, large capacity 141B $1.20/h $0.60/h $0.30/h
Llama 3.1 405BLargest widely used open model 405B over 8× over 8× $1.20/h
This is an estimate for weights, not a benchmark.

Real usage depends on context length, batch size and the serving engine: a long context can add tens of gigabytes of KV cache. Treat the table as the floor, not the ceiling — and if a job is close to the limit, take the next node size or quantise one step further.

Value

What a dollar buys on an L40S.

Ranked 11 of 21 data-center models in this catalogue on cost per gigabyte of GPU memory.

VRAM per dollar
320 GB

GPU memory you get for $1.00 of spot time, per hour.

Memory bandwidth per dollar
5,760 GB/s

Bandwidth decides token throughput far more often than raw FLOPS.

Cost per FP16 TFLOP-hour
$0.00041

Spot price divided by published FP16 tensor throughput.

Cost of a 24-hour run
$3.60

One GPU on spot, billed per minute, storage excluded.

Against the rest of the market

64 providers · September 2026
Median on-demand elsewhere
$1.25Our on-demand is 80% below it
Cheapest on-demand seen
$0.35Our on-demand $0.25 is 29% below it
Cheapest spot seen
$0.28Our spot $0.15 is 46% below it
24 hours on one GPU
$3.60 on spot$6.00 on-demand · $8.40 at the cheapest rate found elsewhere

Index built from published prices for the same GPU across 137 providers (public price index (getdeploying.com)), September 2026. How the guarantee is enforced.

Good for

What people run on an L40S.

Fine-tuning with LoRA and QLoRA

Comfortable for parameter-efficient training on 13B–34B models without sharding.

Inference servers

Holds 30B-class models quantised, or several smaller models side by side.

Anything that can checkpoint

On the spot tier this model is 40% below its own on-demand price, with a 2-minute notice before a reclaim.

Specifications

NVIDIA L40S, as published by NVIDIA.

Taken from the vendor datasheet. Where a figure is not published, the row is absent rather than estimated.

Vendor
NVIDIA
Architecture
Ada Lovelace (2023)
Segment
Datacenter
Memory
48 GB GDDR6
Memory bandwidth
864 GB/s
FP16 / BF16 tensor
362 TFLOPS
FP8 tensor
733 TFLOPS
FP32
92 TFLOPS
CUDA cores
18,176
Board power
350 W
Form factor
PCIe dual-slot
Interconnect
PCIe Gen4 x16 64 GB/s
Multi-instance (MIG)
Not available
8-bit float (FP8)
Supported by the architecture

Source: www.nvidia.com · verified against the vendor document

Software that runs on it

8 templates

Pre-built environments, pulled on the node before you land on it. Or bring any OCI image from a public or private registry.

PyTorch 2.5 · CUDA 12.4CUDA 12.4 basevLLM inferenceJupyterLabComfyUIOllamaTensorFlow 2.17Ubuntu 22.04 (driver only)

All templates

On the spot tier

<5% reclaimed · 30 d
  • 2 minutes of notice on the metadata endpoint, a webhook and the console
  • The instance is stopped, not deleted — disk and IP stay attached
  • Auto-relaunch on the next free L40S, or switch the same disk to on-demand
  • You save $2.40 a day per GPU against on-demand

How interruptions work

FAQ

L40S — the questions that come up

How much does an L40S cost per hour?

Spot is $0.15 per GPU-hour and on-demand is $0.25, both billed per minute — every started minute costs the hourly price divided by 60, so $0.0025 on spot. Reserved capacity is $0.15 per GPU-hour on a monthly commitment. Storage and egress are not included in that rate: persistent disks are $0.08 per GB-month and there are no egress fees.

How many GPUs can I put in one instance?

Node sizes are 1×, 2×, 4×, 8× — up to 8 L40S GPUs in a single virtual machine, with CPU, RAM and local NVMe scaled with the GPU count. The price per GPU is identical at every node size.

Can it run a 70B model?

Yes. At FP8, a 70B model needs about 70 GB for the weights, so it fits on 2× L40S ($0.30 per hour on spot) with roughly 20% of the memory left for activations and the KV cache.

Which regions have it?

Available now in US East (Virginia), US West (Oregon), EU Central (Frankfurt). Prices are identical in every region; pick the one closest to your data.

How often is a spot L40S reclaimed?

Over the trailing 30 days, <5% of spot instances on this model were reclaimed. You get a 2-minute notice on the metadata endpoint, through a webhook and in the console; the instance is then stopped, never deleted, and the persistent disk stays attached.

Anything else about this model? Ask an engineer — the same people run the nodes.

Get started

An L40S for $0.15 an hour, running in under 60 seconds.

Pay as you go — no contracts, no minimum commitment. Add credit, launch, stop whenever you want.

Billed per minute from the moment the instance is reachable. Minimum credit $40, no subscription. 96 L40S GPUs available right now.