GPU Rental Prices
SearchCtrl K

A40 rental price: from $0.59/hr

The cheapest on-demand A40 is $0.59 an hour at RunPod, checked 21 November 2026; the typical provider charges $1.71.

Cheapest on-demand · 48 GB · checked 21 November 2026$0.59/GPU-hourRunPod
  • Provider median $1.71
  • Highest on-demand $2.66
  • 3 offers
  • 3 providers
  • Cheapest +34.1% in 90 days
  • Same offers, 90 days: +15.8%
  • Source runpod.io

A40 offers: 3 configurations from 3 providers

More filters: provider, memory, node size, stock, place, CPU and RAM, sort, price unit

“Machines in” filters the 1 of 3 offers whose provider says where the machine is; the others are under “Place not stated”.

“vCPUs per GPU” and “RAM per GPU” use the 1 of 3 offers whose provider publishes the machine's vCPUs or RAM for a stated number of GPUs (RunPod); an offer that does not publish them never matches a minimum. A GiB counts as 1.07 GB.

3 offers; rates are per GPU and the node total is for the smallest listed node.

3 providers with on-demand offers, fresh prices first, then cheapest. Tap a provider for its configurations.

GPU / providerBilling$/GPU-hourNode · total per hourRent
A40 · RunPod48 GBsecure cloud$0.59–In stock: mediumRent →
checked 21 NovDetails
CPU
9 vCPU
RAM
50 GB RAM
Stock in
Canada, Europe
Checked
21 November 2026

Source price ↗ · Report this price

A40 · Vultr48 GBon-demand$1.711× $1.71In stockRent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

A40 · Runcrate48 GB · A40; lowest live rate; billed per secondon-demandStarting rate$2.66–Rent →
checked 21 NovDetails
Checked
21 November 2026

Source price ↗ · Report this price

Fresh prices come first. Within each billing type, prices run lowest first, with unavailable offers last. Commercial relationships never affect ordering. How we collect and rank prices.

Same GPU, provider, billing and price on several hosts or listings: one row, with the count. – means the provider does not state it.

Cite this data

GPU Rental Prices, "A40 rental price: from $0.59/GPU-hour", prices checked 21 November 2026, https://gpurentalprices.com/a40

Quote it with a link to this page. Downloads of the whole dataset are on Data & API.

On-demand and secure-cloud rates are capacity the provider runs, with no reservation. Spot and community capacity can be interrupted. A marketplace host is one independent owner's server listed on a marketplace. Prices are per GPU per hour, before storage and data transfer. Every row shows the date it was checked.

A40 price history and range

Date range for the A40 chart
  • Cheapest on-demand$0.59(+34.1% in 90 days)
  • Provider median$1.71
  • Cheapest spot$0.35
Daily, 2026-07-05 to 2026-11-21, from our own price checks. The provider median counts each provider's cheapest on-demand rate once and is drawn only on days with three or more providers. Missing days stay gaps.

A40 price range by billing type

Per GPU-hour, latest checked offers. Axis $0 to $4.

On-demand3 offers · 3 providersfrom $0.59median $1.71to $2.66

CheapestProvider median (each provider's cheapest rate counted once; shown with three or more providers)

Price changes

  • 30 days: unchanged across 2 matching on-demand configurations since 22 October 2026.
  • 90 days: +15.8% across 2 matching on-demand configurations since 23 August 2026.

Changes use the geometric mean of price ratios for the same provider, variant, tier, GPU count, instance and region (RunPod's place is where that day's stock sat, so it is not matched). New listings are not counted as price changes. Full ledger on the history hub.

A40 daily figures (140 days)
DateCheapest on-demandProvider medianCheapest spot
2026-11-21$0.59$1.71–
2026-11-20$0.59$1.71–
2026-11-19$0.59$1.71–
2026-11-18$0.59$1.71–
2026-11-17$0.59$1.71–
2026-11-16$0.59$1.71–
2026-11-15$0.59$1.71–
2026-11-14$0.59$1.71–
2026-11-13$0.59$1.71–
2026-11-12$0.59$1.71–
2026-11-11$0.59$1.71–
2026-11-10$0.59$1.71–
2026-11-09$0.59$1.71–
2026-11-08$0.59$1.71–
2026-11-07$0.59$1.71–
2026-11-06$0.59$1.71–
2026-11-05$0.59$1.71–
2026-11-04$0.59$1.71–
2026-11-03$0.59$1.71–
2026-11-02$0.59––
2026-11-01$0.59$1.71–
2026-10-31$0.59––
2026-10-30$0.59––
2026-10-29$0.59––
2026-10-28$0.59––
2026-10-27$0.59––
2026-10-26$0.59––
2026-10-25$0.59––
2026-10-24$0.59––
2026-10-23$0.59––
2026-10-22$0.59––
2026-10-21$0.59––
2026-10-20$0.59––
2026-10-19$0.59––
2026-10-18$0.59––
2026-10-17$0.59––
2026-10-16$0.59––
2026-10-15$0.59––
2026-10-14$0.59––
2026-10-13$0.59––
2026-10-12$0.59––
2026-10-11$0.59––
2026-10-10$0.59––
2026-10-09$0.59––
2026-10-08$0.49––
2026-10-07$0.49––
2026-10-06$0.49––
2026-10-05$0.49––
2026-10-04$0.49––
2026-10-03$0.49––
2026-10-02$0.49––
2026-10-01$0.49––
2026-09-30$0.49––
2026-09-29$0.49––
2026-09-28$0.49––
2026-09-27$0.49––
2026-09-26$0.49––
2026-09-25$0.49––
2026-09-24$0.49––
2026-09-23$0.49––
2026-09-22$0.49––
2026-09-21$0.49––
2026-09-20$0.49––
2026-09-19$0.49––
2026-09-18$0.49––
2026-09-17$0.49––
2026-09-16$0.49––
2026-09-15$0.49––
2026-09-14$0.49––
2026-09-13$0.49––
2026-09-12$0.49––
2026-09-11$0.49––
2026-09-10$0.49––
2026-09-09$0.49––
2026-09-08$0.49––
2026-09-07$0.49––
2026-09-06$0.49––
2026-09-05$0.49––
2026-09-04$0.49––
2026-09-03$0.44––
2026-09-02$0.44––
2026-09-01$0.44––
2026-08-31$0.44––
2026-08-30$0.44––
2026-08-29$0.44––
2026-08-28$0.44––
2026-08-27$0.44––
2026-08-26$0.44––
2026-08-25$0.44––
2026-08-24$0.44––
2026-08-23$0.44––
2026-08-22$0.44––
2026-08-21$0.44––
2026-08-20$0.44––
2026-08-19$0.44––
2026-08-18$0.44––
2026-08-17$0.44––
2026-08-16$0.44––
2026-08-15$0.44––
2026-08-14$0.44––
2026-08-13$0.44––
2026-08-12$0.44––
2026-08-11$0.44––
2026-08-10$0.44––
2026-08-09$0.44––
2026-08-08$0.44––
2026-08-07$0.44–$0.35
2026-08-06$0.44–$0.35
2026-08-05$0.44–$0.35
2026-08-04$0.44–$0.35
2026-08-03$0.44–$0.35
2026-08-02$0.44–$0.35
2026-08-01$0.44–$0.35
2026-07-31$0.44–$0.35
2026-07-30$0.44–$0.35
2026-07-29$0.44–$0.35
2026-07-28$0.44–$0.35
2026-07-27$0.44–$0.35
2026-07-26$0.44–$0.35
2026-07-25$0.44–$0.35
2026-07-24$0.44–$0.35
2026-07-23$0.44–$0.35
2026-07-22$0.44–$0.35
2026-07-21$0.44–$0.35
2026-07-20$0.44–$0.35
2026-07-19$0.44–$0.35
2026-07-18$0.44–$0.35
2026-07-17$0.44–$0.35
2026-07-16$0.44–$0.35
2026-07-15$0.44–$0.35
2026-07-14$0.44–$0.35
2026-07-13$0.44–$0.35
2026-07-12$0.44–$0.35
2026-07-11$0.44–$0.35
2026-07-10$0.44–$0.35
2026-07-09$0.44–$0.35
2026-07-08$0.44–$0.35
2026-07-07$0.44–$0.35
2026-07-06$0.44–$0.35
2026-07-05$0.25–$0.17

A40 prices by provider and billing type

Each provider's cheapest rate in each billing type, per GPU-hour. The provider name opens its A40 page with node sizes, fees and its own history.

ProviderOn-demand
RunPod$0.59
Vultr$1.71
Runcrate$2.66

A40 hardware specs

A40 hardware specifications
ArchitectureAmpere
VRAM48 GB
FP16 TFLOPS (dense)150
Memory bandwidth696 GB/s
TDP300 W
InterconnectNVLink 112.5GB/s
Launched2020

Manufacturer datasheet figures for the A40. Source: images.nvidia.com.

LLM memory estimates for this GPU

Qwen2.5 14B at 16-bit weights
36.4GB
Weights 29.5 GB · cache 0.8 GB · headroom 6.1 GB. Capacity line: 48 GB.

These models have an estimated inference footprint within 48 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.

Model16-bit GB8-bit GB4-bit GB
Qwen2.5 72B176.1 88.9 45.2 ✓
DeepSeek R1 Distill Llama 70B170.9 86.3 43.9 ✓
Mixtral 8x7B v0.1112.7 56.7 28.7 ✓
Qwen2.5 32B79.9 40.6 ✓20.9 ✓
Qwen2.5 Coder 32B79.9 40.6 ✓20.9 ✓
DeepSeek R1 Distill Qwen 32B79.9 40.6 ✓20.9 ✓
QwQ 32B79.9 40.6 ✓20.9 ✓
Qwen3 32B79.9 40.6 ✓20.9 ✓
Qwen3 30B A3B73.8 37.1 ✓18.8 ✓
Qwen3 30B A3B 250773.8 37.1 ✓18.8 ✓
Qwen3 Coder 30B A3B73.8 37.1 ✓18.8 ✓
Mistral Small 3.2 24B 250658.4 29.6 ✓15.2 ✓
Mistral Small 24B 250157.4 29.1 ✓14.9 ✓
Devstral Small 250757.4 29.1 ✓14.9 ✓
Qwen2.5 14B36.4 ✓18.7 ✓9.8 ✓
Qwen2.5 Coder 14B36.4 ✓18.7 ✓9.8 ✓
DeepSeek R1 Distill Qwen 14B36.4 ✓18.7 ✓9.8 ✓
Qwen3 14B36.2 ✓18.5 ✓9.7 ✓
phi 436.2 ✓18.6 ✓9.8 ✓
Phi 4 reasoning36.2 ✓18.6 ✓9.8 ✓
Phi 4 reasoning plus36.2 ✓18.6 ✓9.8 ✓
Mistral Nemo 240730.2 ✓15.5 ✓8.2 ✓
Qwen3 8B20.4 ✓10.6 ✓5.6 ✓
DeepSeek R1 Distill Llama 8B19.9 ✓10.3 ✓5.5 ✓
Qwen2.5 7B18.6 ✓9.4 ✓4.9 ✓
Qwen2.5 Coder 7B18.6 ✓9.4 ✓4.9 ✓
DeepSeek R1 Distill Qwen 7B18.6 ✓9.4 ✓4.9 ✓
Mistral 7B v0.318.0 ✓9.3 ✓5.0 ✓
Qwen3 4B10.4 ✓5.6 ✓3.1 ✓
Qwen3 4B 250710.4 ✓5.6 ✓3.1 ✓
Qwen2.5 3B7.6 ✓3.9 ✓2.0 ✓
Qwen2.5 Coder 3B7.6 ✓3.9 ✓2.0 ✓
Qwen3 1.7B5.4 ✓3.0 ✓1.8 ✓
DeepSeek R1 Distill Qwen 1.5B4.4 ✓2.3 ✓1.2 ✓
Qwen2.5 1.5B3.8 ✓2.0 ✓1.1 ✓
Qwen2.5 Coder 1.5B3.8 ✓2.0 ✓1.1 ✓
Qwen3 0.6B2.4 ✓1.5 ✓1.0 ✓
Qwen2.5 0.5B1.2 ✓0.7 ✓0.4 ✓
Qwen2.5 Coder 0.5B1.2 ✓0.7 ✓0.4 ✓

Models that need more than one A40

Compare model memory requirements or change context and memory assumptions on a model's page.

When to choose the A40, and what to pick instead

Start from memory: your model, its context and your batch must fit in 48 GB (the model-fit table above estimates it). Then the A40 is the right card unless one of these fits your job better.

Rent or buy the A40

Confirmed A40 purchase listings start at $5,800 (A40 48GB, Viperatech, checked 21 November 2026). That sum rents about 9,831 GPU-hours at the cheapest on-demand rate of $0.59 (checked 21 November 2026), about 4.7 years at 40 hours a week, before electricity, hosting and resale.

Compare A40 purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates. Compare two GPUs.

A40 questions

How much does it cost to rent an A40?
The cheapest A40 rental we have is $0.59 per GPU-hour on RunPod (secure cloud), checked 21 November 2026. The median of each provider's cheapest on-demand rate is $1.71 across 3 providers.
How much VRAM does an A40 have?
48 GB.
Where is the A40 cheapest right now?
RunPod has the cheapest checked on-demand rate on 21 November 2026 at $0.59 per GPU-hour.

GPUs near the A40

Related

All 48 GB+ GPUs · GPUs under $1/hr · Price movers this week · RunPod review · L40S vs A40 · A100 vs A40 · A10 vs A40

Compare your offers

Saved prices keep their original dates. Confirm the configuration, terms and availability at the source.

Select up to three offers to compare their rates and terms.

Type a GPU, a provider, a model or a question.