Ranking 01
Cheapest
Lowest true cost per GPU-hour, in stock or stock unknown, newest reading per provider
NVIDIA · Pascal · Datacenter · 11 providers list itNVIDIA Tesla P100 cloud prices
Rented today by 3 providers with a current on-demand offer, from $0.04 to $0.09 per GPU-hour, median $0.07. Every number below links to the page it was read from, with its read date.
Memory16GB
Bandwidth0.73TB/s
FP16 tensor18.7TFLOPS
FP329.3TFLOPS
Power250W
Specifications: manufacturer datasheet citation pending.
Cheapest on-demand · read 21:35 UTC
$0.04/ GPU·h
Vast.aiTrust 781× Tesla P100 · 16 GB · Poland- Median
- $0.07 3 providers, once each
- 30 days
- —
- 90 days
- —
Prices by rental mode · On-demand · Spot · ReservedTesla P100 prices today
Cheapest, median and spread among current offers. Medians count one floor per marketplace and need at least three offers.
Cheapest$0.04Vast.ai
Median$0.07n = 4
Highest$0.09among current offers
Current offers253 providers · last 45 days
Ever listed3910 providers on file
Where today's on-demand offers sitone dot per eligible offer (4) · the pool behind the tiles · read Nov 1, 2026 21:35 UTC
Provider offer2Marketplace floor2Median$0.07Middle half$0.07 – $0.08
4 eligible offers from 3 providers, binned every $0.002: from $0.04 (Vast.ai) to $0.09 (Edgevana). 17 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 1, 2026
Median · all providers$0.07Providers
Today $0.0730 days —92 days —Low $0.05 · Oct 1High $1.46 · Oct 30
Daily median on-demand price per GPU-hour across all providers, 92 days to Nov 1, 2026. Provider lines: the provider's cheapest current on-demand offer, its listed price over the last 30 days (read Nov 1, 2026). Drag to zoom, double-click to reset.
Today's podium · on-demand · readings of the last 45 days · reference Nov 1, 2026 21:35 UTCWho rents the Tesla P100 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
Ranking 03
Most trusted
Highest Trust Score among providers with an eligible offer · unscored providers follow, cheapest first
4 eligible on-demand offers from 3 providers · median $0.07 (n = 4) · not ranked: 1 unavailable, 1 resold · readings of the last 45 days · reference Nov 1, 2026 · 21:35 UTCRankings are never sponsored. How we rank →
All offers · 72 readings on file · 11 providersEvery Tesla P100 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 floor | 1× Tesla P1006 vCPU · 23.4 GB RAM · 1,623.6 GB disk | Poland | In stock | $0.04 | $0.04 | 21:06 UTCfresh | Receipt |
| Vast.aiTrust 78 | 8× Tesla P10080 vCPU · 125.8 GB RAM · 2,681.1 GB disk | US | In stock | $0.05 | $0.05 | 21:07 UTCfresh | Receipt |
| Vast.aiTrust 78 | 8× Tesla P10080 vCPU · 125.8 GB RAM · 2,681.1 GB disk | US | In stock | $0.05 | $0.05 | 21:07 UTCfresh | Receipt |
| Vast.aiTrust 78 | 7× Tesla P10080 vCPU · 125.8 GB RAM · 2,681.1 GB disk | US | In stock | $0.05 | $0.05 | 21:07 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla P10040 vCPU · 62.9 GB RAM · 1,340.5 GB disk | US | In stock | $0.05 | $0.05 | 21:07 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× Tesla P10020 vCPU · 31.4 GB RAM · 670.3 GB disk | US | In stock | $0.05 | $0.05 | 21:07 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× Tesla P10020 vCPU · 31.4 GB RAM · 670.3 GB disk | US | In stock | $0.05 | $0.05 | 21:07 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× Tesla P10010 vCPU · 15.7 GB RAM · 335.1 GB disk | US | In stock | $0.05 | $0.05 | 21:07 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× Tesla P10010 vCPU · 15.7 GB RAM · 334.1 GB disk | US | In stock | $0.05 | $0.05 | 21:07 UTCfresh | Receipt |
| 1× Tesla P10012 vCPU · 16 GB RAM · 512 GB disk | Korea | Stock unknown | $0.07 | $0.07 | 21:13 UTCfresh | Receipt | |
| 1× Tesla P10012 vCPU · 16 GB RAM · 512 GB disk | Korea | Stock unknown | $0.07 | $0.07 | 21:13 UTCfresh | Receipt | |
| Vast.aiTrust 78 | 2× Tesla P10024 vCPU · 41.9 GB RAM · 1,050 GB disk | Canada | In stock | $0.08 | $0.08 | 21:06 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla P10048 vCPU · 62.8 GB RAM · 166 GB disk | Canada | In stock | $0.08 | $0.08 | 21:05 UTCfresh | Receipt |
 Omega Gradientresold from Sesterce Cloud | 4× Tesla P10048 vCPU · 63 GB RAM · 166 GB disk | Global · flexible | In stock | $0.09 | $0.09 | 21:10 UTCfresh | Receipt |
| Edgevanamarketplace floor | 4× Tesla P10048 vCPU · 63 GB RAM · 166 GB disk | Canada | In stock | $0.09 | $0.09 | 21:11 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla P10024 vCPU · 92.9 GB RAM · 2,753 GB disk | US | In stock | $0.09 | $0.09 | 21:05 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× Tesla P10048 vCPU · 62.7 GB RAM · 118 GB disk | Canada | In stock | $0.09 | $0.09 | 21:07 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× Tesla P10012 vCPU · 46.5 GB RAM · 1,376.5 GB disk | US | In stock | $0.10 | $0.10 | 21:05 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× Tesla P10024 vCPU · 31.3 GB RAM · 59 GB disk | Canada | In stock | $0.10 | $0.10 | 21:07 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× Tesla P1006 vCPU · 23.2 GB RAM · 688.2 GB disk | US | In stock | $0.10 | $0.10 | 21:05 UTCfresh | Receipt |
| Edgevana | 4× Tesla P10048 vCPU · 63 GB RAM · 118 GB disk | Canada | In stock | $0.11 | $0.11 | 21:11 UTCfresh | Receipt |
 LeaderGPUTrust 59 | 2× Tesla P100256 GB RAM | LeaderGPU data centres (EU) | Unavailable | $0.42 | $0.42 | 21:10 UTCfresh | Receipt |
 ScalewayTrust 85outlier · suspended | 1× Tesla P10010 vCPU · 42 GB RAM | France | Stock unknown | $1.36 | $1.36 | 21:11 UTCfresh | Receipt |
| ScalewayTrust 85outlier · suspended | 1× Tesla P10010 vCPU · 42 GB RAM | France | In stock | $1.36 | $1.36 | 21:11 UTCfresh | Receipt |
 Google CloudTrust 78outlier · suspended | 1× Tesla P100 | Australia +19 | Stock unknown | $1.46 | $1.46 | 21:10 UTCfresh | Receipt |
25 fresh offers · 14 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 · hour16 GB | $0.003 | $0.005 |
| per PFLOP FP16 · hour18.7 TFLOPS | $2.401 | $4.005 |
| per TB/s of bandwidth · hour0.73 TB/s | $0.061 | $0.102 |
| Model | Needs | Smallest config | $ / month |
|---|---|---|---|
| all MiniLM L6 v2Sentence Transformers | 1 GBFP8 | 1× Tesla P100at Vast.ai | $33 |
| paraphrase multilingual MiniLM L12 v2Sentence Transformers | 1 GBFP8 | 1× Tesla P100at Vast.ai | $33 |
| bge-m3BAAI | 1 GBFP8 | 1× Tesla P100at Vast.ai | $33 |
| Qwen3 0.6BQwen | 1 GBFP8 | 1× Tesla P100at Vast.ai | $33 |
| all-mpnet-base-v2Sentence Transformers | 1 GBFP8 | 1× Tesla P100at Vast.ai | $33 |
| bge-reranker-v2-m3BAAI | 1 GBFP8 | 1× Tesla P100at Vast.ai | $33 |
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 P100 · comparisons and collectionsCompare the Tesla P100 side by side
Questions about renting the Tesla P100
How much does the Tesla P100 cost per hour?
Today the Tesla P100 rents from $0.04 per GPU-hour on-demand, with a median of $0.07 across 3 providers, each counted once at its cheapest current offer (4 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 P100?
6 providers have a current Tesla P100 offer in stock. Cheapest first: Vast Ai ($0.04), Gcube ($0.07), Omega Gradient ($0.09), Edgevana ($0.09), Scaleway ($1.36), Google Cloud ($1.46). Older readings from other providers stay listed on this page, in grey, and are never ranked.
How much memory does the Tesla P100 have?
16 GB of memory at 0.73 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 P100 cheapest right now?
The lowest true cost among eligible offers is $0.04 per GPU-hour at Vast.ai for a 1-GPU machine in Poland, 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 P100 cheaper on spot or reserved?
Spot (interruptible) capacity starts at $0.04 per GPU-hour; reserved terms start at $0.22. Spot suits jobs that checkpoint; reserved suits machines that run all month.