Ranking 01
Cheapest
Lowest true cost per GPU-hour, in stock or stock unknown, newest reading per provider
Vast.ai2× · Belgium$0.47
LeaderGPU8× · 00:19 UTC$0.58- 4
Denvr Cloud4× · 00:32 UTC$0.65 - 5
Edgevana4× · Belgium$0.75
NVIDIA · Ampere · Datacenter · 26 providers list itNVIDIA A40 cloud prices
Rented today by 10 providers with a current on-demand offer, from $0.35 to $1.71 per GPU-hour, median $0.90. Every number below links to the page it was read from, with its read date.
Memory48GB
Bandwidth0.70TB/s
FP16 tensor150TFLOPS
FP3237.4TFLOPS
Power300W
Specifications: manufacturer figures.
Cheapest on-demand · read 00:32 UTC
$0.35/ GPU·h
GPURento1× A40 · 48 GB · Germany · France- Median
- $0.90 10 providers, once each
- 30 days
- —
- 90 days
- +33.1%
Prices by rental mode · On-demand · Spot · Reserved · ServerlessA40 prices today
Cheapest, median and spread among current offers. Medians count one floor per marketplace and need at least three offers.
Cheapest$0.35GPURento
Median$0.90n = 13
Highest$1.71among current offers
Current offers4310 providers · last 45 days
Ever listed9722 providers on file
Where today's on-demand offers sitone dot per eligible offer (13) · the pool behind the tiles · read Nov 2, 2026 00:32 UTC
Provider offer10Marketplace floor3Median$0.90Middle half$0.65 – $1.05
13 eligible offers from 10 providers, binned every $0.05: from $0.35 (GPURento) to $1.71 (Vultr). 16 further marketplace listings sit above their marketplace's floor and are not drawn (one floor per marketplace, as in the tiles). Hover a dot for the provider, price, configuration, region and read date; click it to open the provider.
On-demand price history · 92 daysdaily median across all providers · 3 provider lines from their 30-day series · read Nov 2, 2026
Median · all providers$0.90Providers
Today $0.9030 days —92 days +33.1%Low $0.65 · Oct 30High $1.96 · Aug 5
Daily median on-demand price per GPU-hour across all providers, 92 days to Nov 2, 2026. Provider lines: the provider's cheapest current on-demand offer, its listed price over the last 30 days (read Nov 2, 2026). Drag to zoom, double-click to reset.
Today's podium · on-demand · readings of the last 45 days · reference Nov 2, 2026 00:32 UTCWho rents the A40 best today
Cheapest true cost, best throughput per dollar, highest Trust Score. One provider per step, ten places, every row dated.
Ranking 02
Best value
Most throughput per dollar for LLM inference · Trust ≥ 60 first, then provisional · estimated
- Denvr Cloud4× · 00:32 UTCValue 55$0.65
Exoscale4× · GermanyValue 32$1.05- 4
E2E Networks1× · IndiaValue 17$1.44
- 5
Vultr1× · USValue 12$1.71
Ranking 03
Most trusted
Highest Trust Score among providers with an eligible offer · unscored providers follow, cheapest first
- Exoscale1× · GermanyTrust 84$1.05
- Vast.ai2× · BelgiumTrust 78$0.47
- 4Vultr1× · USTrust 75$1.71
- 5Denvr Cloud4× · 00:32 UTCTrust 67$0.65
13 eligible on-demand offers from 10 providers · median $0.90 (n = 13) · not ranked: 10 unavailable, 1 resold, 1 older readings · readings of the last 45 days · reference Nov 2, 2026 · 00:32 UTCRankings are never sponsored. How we rank →
All offers · 159 readings on file · 26 providersEvery A40 offer, with its receipt
Current offers ranked by true cost, each with its read date. Older readings stay listed below, in grey, and never enter a ranking.
| Provider | Configuration | Region | Stock | List | True cost | Read | |
|---|---|---|---|---|---|---|---|
| GPURento | 1× A40 | Germany · France | Stock unknown | $0.35 | $0.35 | 00:25 UTCfresh | Receipt |
| Vast.aiTrust 78marketplace floor | 2× A40128 vCPU · 1,001.9 GB RAM · 11 GB disk | Belgium | In stock | $0.47 | $0.47 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× A4064 vCPU · 125.8 GB RAM · 249.2 GB disk | US | In stock | $0.48 | $0.48 | 00:00 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× A4032 vCPU · 62.9 GB RAM · 124.6 GB disk | US | In stock | $0.48 | $0.48 | 00:00 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× A4064 vCPU · 501 GB RAM · 2,545.8 GB disk | Belgium | In stock | $0.50 | $0.50 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× A4020 vCPU · 125.5 GB RAM · 2,882 GB disk | UK | In stock | $0.54 | $0.54 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× A40256 vCPU · 2,003.8 GB RAM · 882.8 GB disk | Belgium | In stock | $0.57 | $0.57 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× A40128 vCPU · 1,001.9 GB RAM · 441.4 GB disk | Belgium | In stock | $0.57 | $0.57 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× A40128 vCPU · 1,001.9 GB RAM · 439.6 GB disk | Belgium | In stock | $0.57 | $0.57 | 00:02 UTCfresh | Receipt |
| LeaderGPUTrust 59 | 8× A40384 GB RAM | LeaderGPU data centres (EU) | In stock | $0.58 | $0.58 | 00:19 UTCfresh | Receipt |
 RunpodTrust 95 | 1× A40 | Runpod Secure Cloud datacenters | Unavailable | $0.59 | $0.59 | 00:03 UTCfresh | Receipt |
| Denvr CloudTrust 67 | 4× A40 | — | Stock unknown | $0.65 | $0.65 | 00:32 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× A40256 vCPU · 2,003.8 GB RAM · 1,473 GB disk | Belgium | In stock | $0.65 | $0.65 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× A40256 vCPU · 1,877.8 GB RAM · 499 GB disk | Belgium | In stock | $0.65 | $0.65 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× A40128 vCPU · 1,001.9 GB RAM · 736.5 GB disk | Belgium | In stock | $0.65 | $0.65 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× A40128 vCPU · 938.9 GB RAM · 249.5 GB disk | Belgium | In stock | $0.65 | $0.65 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× A4064 vCPU · 472.4 GB RAM · 245.8 GB disk | Belgium | In stock | $0.66 | $0.66 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× A4064 vCPU · 501 GB RAM · 2,919.8 GB disk | Belgium | In stock | $0.66 | $0.66 | 00:02 UTCfresh | Receipt |
| Edgevanamarketplace floor | 4× A40256 vCPU · 2,004 GB RAM · 1,473 GB disk | Belgium | In stock | $0.75 | $0.75 | 00:21 UTCfresh | Receipt |
| Edgevana | 4× A40256 vCPU · 1,878 GB RAM · 499 GB disk | Belgium | In stock | $0.75 | $0.75 | 00:21 UTCfresh | Receipt |
| 1× A40 | Lithuania | Unavailable | $0.77 | $0.77 | 00:19 UTCfresh | Receipt | |
| ExoscaleTrust 84 | 1× A4012 vCPU · 56 GB RAM | Germany | Stock unknown | $1.05 | $1.05 | 00:20 UTCfresh | Receipt |
| ExoscaleTrust 84 | 4× A4048 vCPU · 224 GB RAM | Germany | Stock unknown | $1.05 | $1.05 | 00:20 UTCfresh | Receipt |
| ExoscaleTrust 84 | 8× A4096 vCPU · 448 GB RAM | Germany | Stock unknown | $1.05 | $1.05 | 00:20 UTCfresh | Receipt |
| ExoscaleTrust 84 | 2× A4024 vCPU · 120 GB RAM | Germany | Stock unknown | $1.05 | $1.05 | 00:20 UTCfresh | Receipt |
43 fresh offers · the 25 cheapest shown here, all of them in the comparison tool · 54 older readings of the same provider replaced by a newer one · prices per GPU-hour · true cost includes the add-ons the provider publishesOpen in the comparison tool →
Value · what the hour buysPrice per unit, and what fits
The same hour, divided by what the card gives you; then the smallest real configuration for the most downloaded open models.
| Unit | At the cheapest | At the median |
|---|---|---|
| per GB of VRAM · hour48 GB | $0.007 | $0.019 |
| per PFLOP FP16 · hour150 TFLOPS | $2.333 | $5.991 |
| per TB/s of bandwidth · hour0.70 TB/s | $0.503 | $1.291 |
| Model | Needs | Smallest config | $ / month |
|---|---|---|---|
| all MiniLM L6 v2Sentence Transformers | 1 GBFP8 | 1× A40at GPURento | $255 |
| paraphrase multilingual MiniLM L12 v2Sentence Transformers | 1 GBFP8 | 1× A40at GPURento | $255 |
| bge-m3BAAI | 1 GBFP8 | 1× A40at GPURento | $255 |
| Qwen3 0.6BQwen | 1 GBFP8 | 1× A40at GPURento | $255 |
| all-mpnet-base-v2Sentence Transformers | 1 GBFP8 | 1× A40at GPURento | $255 |
| bge-reranker-v2-m3BAAI | 1 GBFP8 | 1× A40at GPURento | $255 |
Monthly = 730 hours at the cheapest current on-demand price for that GPU count · models sized at FP8 when available, weights plus runtime overheadSize any model →
A40 · comparisons and collectionsCompare the A40 side by side
Questions about renting the A40
How much does the A40 cost per hour?
Today the A40 rents from $0.35 per GPU-hour on-demand, with a median of $0.90 across 10 providers, each counted once at its cheapest current offer (13 current offers in all, readings of the last 45 days). Prices depend on the provider, the number of GPUs in the machine, the region and whether you rent on-demand, spot or reserved; true cost adds the mandatory add-ons each provider publishes.
Which cloud providers offer the A40?
12 providers have a current A40 offer in stock. Cheapest first: Gpurento ($0.35), Vast Ai ($0.47), Leadergpu ($0.58), Denvr Cloud ($0.65), Edgevana ($0.75), Exoscale ($1.05). Older readings from other providers stay listed on this page, in grey, and are never ranked.
How much memory does the A40 have?
48 GB of memory at 0.70 TB/s. At FP8 that fits all MiniLM L6 v2 (1 GB), paraphrase multilingual MiniLM L12 v2 (1 GB), bge-m3 (1 GB), Qwen3 0.6B (1 GB), all-mpnet-base-v2 (1 GB) on a single card; larger models need two to eight GPUs or a different card.
Where is the A40 cheapest right now?
The lowest true cost among eligible offers is $0.35 per GPU-hour at GPURento for a 1-GPU machine in Germany · France, read within the ranking window. Offers marked unavailable, older than 45 days, superseded by a newer reading, resold or outside the outlier band are listed but not ranked.
Is the A40 cheaper on spot or reserved?
Spot (interruptible) capacity starts at $0.19 per GPU-hour; reserved terms start at $0.36. Spot suits jobs that checkpoint; reserved suits machines that run all month.