Ranking 01
Cheapest
Lowest true cost per GPU-hour, in stock or stock unknown, newest reading per provider
Cyfuture AI8× · 00:19 UTC$0.55
VoltageGPU8× · Japan$1.10- 4
io.net2× · India$1.26 - 5
E2E Networks1× · India$1.50
NVIDIA · Volta · Datacenter · 35 providers list itNVIDIA Tesla V100 32GB cloud prices
Rented today by 17 providers with a current on-demand offer, from $0.55 to $4.39 per GPU-hour, median $2.48. Every number below links to the page it was read from, with its read date.
Memory32GB
Bandwidth0.90TB/s
FP16 tensor125TFLOPS
FP3215.7TFLOPS
Power300W
Specifications: manufacturer figures.
Cheapest on-demand · read 00:32 UTC
$0.55/ GPU·h
LiumTrust 408× Tesla V100 32GB · 32 GB · HK- Median
- $2.48 17 providers, once each
- 30 days
- 0.0%
- 90 days
- −45.2%
Prices by rental mode · On-demand · Spot · Reserved · ServerlessTesla V100 32GB prices today
Cheapest, median and spread among current offers. Medians count one floor per marketplace and need at least three offers.
Cheapest$0.55Lium
Median$2.48n = 63
Highest$4.39among current offers
Current offers40117 providers · last 45 days
Ever listed42633 providers on file
Where today's on-demand offers sitone dot per eligible offer (63) · the pool behind the tiles · read Nov 2, 2026 00:32 UTC
Provider offer61Marketplace floor2Median$2.48Middle half$1.91 – $3.24
63 eligible offers from 17 providers, binned every $0.20: from $0.55 (Lium) to $4.39 (Volcano Engine). 260 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$2.48Providers
Today $2.4830 days 0.0%92 days -45.2%Low $0.36 · Oct 26High $2.57 · Aug 2
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 Tesla V100 32GB 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
Sesterce Cloud4× · USValue 7$2.57
Microsoft Azure8× · Netherlands +2Value 6$2.75
- 4
AWS8× · Ireland +2Value 1$3.90 - 5Lium8× · HKValue 75prov.$0.55
Ranking 03
Most trusted
Highest Trust Score among providers with an eligible offer · unscored providers follow, cheapest first
- AWS8× · Ireland +2Trust 79$3.90
- 4
- 5io.net2× · IndiaTrust 42$1.26
63 eligible on-demand offers from 17 providers · median $2.48 (n = 63) · not ranked: 53 unavailable, 7 resold · readings of the last 45 days · reference Nov 2, 2026 · 00:32 UTCRankings are never sponsored. How we rank →
All offers · 797 readings on file · 35 providersEvery Tesla V100 32GB 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 | |
|---|---|---|---|---|---|---|---|
 Vast.aiTrust 78marketplace flooroutlier · suspended | 8× Tesla V100 32GB80 vCPU · 376.5 GB RAM · 1,496.5 GB disk | US | In stock | $0.07 | $0.07 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 8× Tesla V100 32GB80 vCPU · 251.5 GB RAM · 591 GB disk | US | In stock | $0.07 | $0.07 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla V100 32GB40 vCPU · 188.3 GB RAM · 735.7 GB disk | US | In stock | $0.07 | $0.07 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla V100 32GB40 vCPU · 125.5 GB RAM · 207.5 GB disk | US | In stock | $0.07 | $0.07 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla V100 32GB40 vCPU · 188.3 GB RAM · 472.6 GB disk | US | In stock | $0.07 | $0.07 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla V100 32GB40 vCPU · 125.8 GB RAM · 295.5 GB disk | US | In stock | $0.07 | $0.07 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× Tesla V100 32GB20 vCPU · 94.1 GB RAM · 367.9 GB disk | US | In stock | $0.07 | $0.07 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× Tesla V100 32GB20 vCPU · 62.8 GB RAM · 103.7 GB disk | US | In stock | $0.07 | $0.07 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× Tesla V100 32GB20 vCPU · 94.1 GB RAM · 236.3 GB disk | US | In stock | $0.07 | $0.07 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× Tesla V100 32GB20 vCPU · 62.9 GB RAM · 147.8 GB disk | US | In stock | $0.07 | $0.07 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× Tesla V100 32GB10 vCPU · 31.4 GB RAM · 64.5 GB disk | US | In stock | $0.07 | $0.07 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× Tesla V100 32GB10 vCPU · 47.1 GB RAM · 104.6 GB disk | US | In stock | $0.07 | $0.07 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 8× Tesla V100 32GB80 vCPU · 376.5 GB RAM · 1,320 GB disk | US | In stock | $0.08 | $0.08 | 00:00 UTCfresh | Receipt |
| Vast.aiTrust 78 | 8× Tesla V100 32GB80 vCPU · 251.5 GB RAM · 580 GB disk | US | In stock | $0.08 | $0.08 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 8× Tesla V100 32GB80 vCPU · 376.5 GB RAM · 683 GB disk | US | In stock | $0.08 | $0.08 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 8× Tesla V100 32GB80 vCPU · 376.5 GB RAM · 1,503.4 GB disk | US | In stock | $0.08 | $0.08 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 8× Tesla V100 32GB80 vCPU · 376.5 GB RAM · 38 GB disk | US | In stock | $0.08 | $0.08 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 8× Tesla V100 32GB80 vCPU · 376.5 GB RAM · 1,507.4 GB disk | US | In stock | $0.08 | $0.08 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla V100 32GB40 vCPU · 125.5 GB RAM · 278 GB disk | US | In stock | $0.08 | $0.08 | 00:00 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla V100 32GB40 vCPU · 188.3 GB RAM · 660 GB disk | US | In stock | $0.08 | $0.08 | 00:00 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla V100 32GB40 vCPU · 125.8 GB RAM · 272 GB disk | US | In stock | $0.08 | $0.08 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla V100 32GB40 vCPU · 188.3 GB RAM · 341.5 GB disk | US | In stock | $0.08 | $0.08 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla V100 32GB40 vCPU · 188.3 GB RAM · 751.7 GB disk | US | In stock | $0.08 | $0.08 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla V100 32GB40 vCPU · 188.3 GB RAM · 19 GB disk | US | In stock | $0.08 | $0.08 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla V100 32GB40 vCPU · 188.3 GB RAM · 753.7 GB disk | US | In stock | $0.08 | $0.08 | 00:02 UTCfresh | Receipt |
401 fresh offers · the 25 cheapest shown here, all of them in the comparison tool · 25 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 · hour32 GB | $0.017 | $0.078 |
| per PFLOP FP16 · hour125 TFLOPS | $4.400 | $19.862 |
| per TB/s of bandwidth · hour0.90 TB/s | $0.611 | $2.759 |
| Model | Needs | Smallest config | $ / month |
|---|---|---|---|
| all MiniLM L6 v2Sentence Transformers | 1 GBFP8 | 1× Tesla V100 32GBat Vast.ai | $50 |
| paraphrase multilingual MiniLM L12 v2Sentence Transformers | 1 GBFP8 | 1× Tesla V100 32GBat Vast.ai | $50 |
| bge-m3BAAI | 1 GBFP8 | 1× Tesla V100 32GBat Vast.ai | $50 |
| Qwen3 0.6BQwen | 1 GBFP8 | 1× Tesla V100 32GBat Vast.ai | $50 |
| all-mpnet-base-v2Sentence Transformers | 1 GBFP8 | 1× Tesla V100 32GBat Vast.ai | $50 |
| bge-reranker-v2-m3BAAI | 1 GBFP8 | 1× Tesla V100 32GBat Vast.ai | $50 |
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 →
Tesla V100 32GB · comparisons and collectionsCompare the Tesla V100 32GB side by side
Questions about renting the Tesla V100 32GB
How much does the Tesla V100 32GB cost per hour?
Today the Tesla V100 32GB rents from $0.55 per GPU-hour on-demand, with a median of $2.48 across 17 providers, each counted once at its cheapest current offer (63 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 Tesla V100 32GB?
27 providers have a current Tesla V100 32GB offer in stock. Cheapest first: Vast Ai ($0.07), Clore Ai ($0.09), Akash Network ($0.18), Edgevana ($0.23), Runcrate ($0.36), Atmoscompute ($0.36). Older readings from other providers stay listed on this page, in grey, and are never ranked.
How much memory does the Tesla V100 32GB have?
32 GB of memory at 0.90 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 Tesla V100 32GB cheapest right now?
The lowest true cost among eligible offers is $0.55 per GPU-hour at Lium for a 8-GPU machine in HK, 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 Tesla V100 32GB cheaper on spot or reserved?
Spot (interruptible) capacity starts at $0.51 per GPU-hour; reserved terms start at $0.27. Spot suits jobs that checkpoint; reserved suits machines that run all month.