Cheapest
Lowest true cost per GPU-hour, in stock or stock unknown, newest reading per provider
OVHcloud2× · 21:09 UTC$0.78
Lambda8× · US$0.79- 4
Exoscale4× · Austria$0.83 - 5
Theta EdgeCloud1× · 21:10 UTC$0.99
Rented today by 15 providers with a current on-demand offer, from $0.33 to $3.06 per GPU-hour, median $1.71. Every number below links to the page it was read from, with its read date.
Specifications: manufacturer figures.
Cheapest, median and spread among current offers. Medians count one floor per marketplace and need at least three offers.
Today's podium · on-demand · readings of the last 45 days · reference Nov 1, 2026 21:35 UTCCheapest true cost, best throughput per dollar, highest Trust Score. One provider per step, ten places, every row dated.

Lambda8× · US$0.79
Lambda8× · USValue 59$0.79


Lambda8× · USTrust 80$0.79Current 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 | |
|---|---|---|---|---|---|---|---|
| 1× Tesla V100 16GB4 vCPU · 64 GB RAM · 65.016 GB disk | US | Unavailable | $0.05 | $0.05 | 21:08 UTCfresh | Receipt | |
| 1× Tesla V100 16GB2 vCPU · 16 GB RAM · 145.572 GB disk | US | Unavailable | $0.05 | $0.05 | 21:08 UTCfresh | Receipt | |
| 1× Tesla V100 16GB2 vCPU · 16 GB RAM · 138.651 GB disk | Taiwan | Unavailable | $0.05 | $0.05 | 21:08 UTCfresh | Receipt | |
| 1× Tesla V100 16GB2 vCPU · 16 GB RAM · 151.215 GB disk | US | In stock | $0.05 | $0.05 | 21:08 UTCfresh | Receipt | |
| 1× Tesla V100 16GB4 vCPU · 32 GB RAM · 166.874 GB disk | US | Unavailable | $0.05 | $0.05 | 21:08 UTCfresh | Receipt | |
| 1× Tesla V100 16GB4 vCPU · 32 GB RAM · 37.034 GB disk | Taiwan | Unavailable | $0.05 | $0.05 | 21:08 UTCfresh | Receipt | |
| 1× Tesla V100 16GB4 vCPU · 32 GB RAM · 21.944 GB disk | Netherlands | Unavailable | $0.05 | $0.05 | 21:08 UTCfresh | Receipt | |
| 1× Tesla V100 16GB4 vCPU · 32 GB RAM · 37.729 GB disk | US | Unavailable | $0.05 | $0.05 | 21:08 UTCfresh | Receipt | |
| 2× Tesla V100 16GB6 vCPU · 32 GB RAM · 2,032 GB disk | US | Unavailable | $0.05 | $0.05 | 21:08 UTCfresh | Receipt | |
| 1× Tesla V100 16GB2 vCPU · 16 GB RAM · 155.147 GB disk | US | In stock | $0.06 | $0.06 | 21:08 UTCfresh | Receipt | |
| 1× Tesla V100 16GB28 vCPU · 46.9 GB RAM · 419.4 GB disk | Canada | In stock | $0.07 | $0.07 | 21:07 UTCfresh | Receipt | |
| 1× Tesla V100 16GB18 vCPU · 16 GB RAM · 23.403 GB disk | Romania | Unavailable | $0.07 | $0.07 | 21:08 UTCfresh | Receipt | |
| 1× Tesla V100 16GB12 vCPU · 16 GB RAM · 63.987 GB disk | Romania | Unavailable | $0.07 | $0.07 | 21:08 UTCfresh | Receipt | |
| 1× Tesla V100 16GB8 vCPU · 16 GB RAM · 53.86 GB disk | Romania | Unavailable | $0.07 | $0.07 | 21:08 UTCfresh | Receipt | |
| 2× Tesla V100 16GB37.33333333333333 vCPU · 41.8 GB RAM · 912.7 GB disk | China | In stock | $0.08 | $0.08 | 21:06 UTCfresh | Receipt | |
| 1× Tesla V100 16GB18.666666666666664 vCPU · 20.9 GB RAM · 456.3 GB disk | China | In stock | $0.08 | $0.08 | 21:06 UTCfresh | Receipt | |
| 1× Tesla V100 16GB8 vCPU · 31.3 GB RAM · 8,163 GB disk | Saudi Arabia | In stock | $0.08 | $0.08 | 21:05 UTCfresh | Receipt | |
| 8× Tesla V100 16GB80 vCPU · 220.2 GB RAM · 2,105.1 GB disk | US | In stock | $0.09 | $0.09 | 21:06 UTCfresh | Receipt | |
| 4× Tesla V100 16GB40 vCPU · 110.1 GB RAM · 1,052.5 GB disk | US | In stock | $0.09 | $0.09 | 21:06 UTCfresh | Receipt | |
| 2× Tesla V100 16GB20 vCPU · 55.1 GB RAM · 526.3 GB disk | US | In stock | $0.09 | $0.09 | 21:06 UTCfresh | Receipt | |
| 2× Tesla V100 16GB64 vCPU · 62.7 GB RAM · 165.1 GB disk | US | In stock | $0.09 | $0.09 | 21:06 UTCfresh | Receipt | |
| 1× Tesla V100 16GB10 vCPU · 27.5 GB RAM · 263.1 GB disk | US | In stock | $0.10 | $0.10 | 21:06 UTCfresh | Receipt | |
| 1× Tesla V100 16GB10 vCPU · 31.3 GB RAM · 386.9 GB disk | US | In stock | $0.10 | $0.10 | 21:06 UTCfresh | Receipt | |
| 1× Tesla V100 16GB32 vCPU · 31.3 GB RAM · 82.5 GB disk | US | In stock | $0.10 | $0.10 | 21:06 UTCfresh | Receipt | |
| 1× Tesla V100 16GB20 vCPU · 43.2 GB RAM · 708.5 GB disk | US | In stock | $0.11 | $0.11 | 21:05 UTCfresh | Receipt |
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 | $0.020 | $0.107 |
| per PFLOP FP16 · hour112 TFLOPS | $2.902 | $15.268 |
| per TB/s of bandwidth · hour0.90 TB/s | $0.361 | $1.900 |
| Model | Needs | Smallest config | $ / month |
|---|---|---|---|
| all MiniLM L6 v2Sentence Transformers | 1 GBFP8 | 1× Tesla V100 16GBat Clore.ai | $46 |
| paraphrase multilingual MiniLM L12 v2Sentence Transformers | 1 GBFP8 | 1× Tesla V100 16GBat Clore.ai | $46 |
| bge-m3BAAI | 1 GBFP8 | 1× Tesla V100 16GBat Clore.ai | $46 |
| Qwen3 0.6BQwen | 1 GBFP8 | 1× Tesla V100 16GBat Clore.ai | $46 |
| all-mpnet-base-v2Sentence Transformers | 1 GBFP8 | 1× Tesla V100 16GBat Clore.ai | $46 |
| bge-reranker-v2-m3BAAI | 1 GBFP8 | 1× Tesla V100 16GBat Clore.ai | $46 |
Today the Tesla V100 16GB rents from $0.33 per GPU-hour on-demand, with a median of $1.71 across 15 providers, each counted once at its cheapest current offer (36 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.
28 providers have a current Tesla V100 16GB offer in stock. Cheapest first: Clore Ai ($0.05), Vast Ai ($0.07), Geodd ($0.16), Tensordock ($0.17), Lium ($0.21), Datacrunch ($0.24). Older readings from other providers stay listed on this page, in grey, and are never ranked.
16 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.
The lowest true cost among eligible offers is $0.33 per GPU-hour at AtmosCompute for a 2-GPU machine, 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.
Spot (interruptible) capacity starts at $0.04 per GPU-hour; reserved terms start at $0.35. Spot suits jobs that checkpoint; reserved suits machines that run all month.