Ranking 01
Cheapest
Lowest true cost per GPU-hour, in stock or stock unknown, newest reading per provider
Tencent CloudOct 25$1.02
Lambda1× · US$1.29- 4
Prime IntellectUS$1.29 - 5
IONOS1× · 00:23 UTC$1.35
NVIDIA · Ampere · Datacenter · 23 providers list itNVIDIA A10 cloud prices
Rented today by 9 providers with a current on-demand offer, from $0.41 to $3.26 per GPU-hour, median $1.35. Every number below links to the page it was read from, with its read date.
Memory24GB
Bandwidth0.60TB/s
FP16 tensor125TFLOPS
FP3231.2TFLOPS
Power150W
Specifications: manufacturer figures.
Cheapest on-demand · read 00:32 UTC
$0.41/ GPU·h
LeaderGPUTrust 5910× A10 · 24 GB · LeaderGPU data centres (EU)- Median
- $1.35 9 providers, once each
- 30 days
- 0.0%
- 90 days
- −4.2%
Prices by rental mode · On-demand · Spot · Reserved · ServerlessA10 prices today
Cheapest, median and spread among current offers. Medians count one floor per marketplace and need at least three offers.
Cheapest$0.41LeaderGPU
Median$1.35n = 19
Highest$3.26among current offers
Current offers399 providers · last 45 days
Ever listed7018 providers on file
Where today's on-demand offers sitone dot per eligible offer (19) · the pool behind the tiles · read Nov 2, 2026 00:32 UTC
Provider offer17Marketplace floor2Median$1.35Middle half$1.39 – $1.66
19 eligible offers from 9 providers, binned every $0.10: from $0.41 (LeaderGPU) to $3.26 (Microsoft Azure). 15 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 · 90 daysdaily median across all providers · 5 provider lines from their 30-day series · read Nov 2, 2026
Median · all providers$1.35Providers
Today $1.3530 days 0.0%90 days -4.2%Low $0.27 · Aug 13High $1.42 · Aug 2
Daily median on-demand price per GPU-hour across all providers, 90 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 A10 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 Cloud1× · USValue 12$1.42
Microsoft Azure1× · UAE +23Value 0$3.20
- 4LeaderGPU10× · 00:19 UTCValue 70prov.$0.41
- 5
Ranking 03
Most trusted
Highest Trust Score among providers with an eligible offer · unscored providers follow, cheapest first
- Lambda1× · USTrust 80$1.29
- 4LeaderGPU10× · 00:19 UTCTrust 59$0.41
- 5
Spheron1× · daf1e228:dulles-usa-1Trust 53$1.55
19 eligible on-demand offers from 9 providers · median $1.35 (n = 19) · not ranked: 1 unavailable, 4 resold · readings of the last 45 days · reference Nov 2, 2026 · 00:32 UTCRankings are never sponsored. How we rank →
All offers · 189 readings on file · 23 providersEvery A10 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 | 2× A1032 vCPU · 62.9 GB RAM · 665.9 GB disk | US | In stock | $0.23 | $0.23 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× A1016 vCPU · 31.4 GB RAM · 332.9 GB disk | US | In stock | $0.23 | $0.23 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× A1096 vCPU · 251.3 GB RAM · 2,765 GB disk | US | In stock | $0.24 | $0.24 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× A1048 vCPU · 125.7 GB RAM · 1,339 GB disk | Netherlands | In stock | $0.24 | $0.24 | 00:00 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× A1048 vCPU · 125.7 GB RAM · 1,472.8 GB disk | US | In stock | $0.24 | $0.24 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× A1048 vCPU · 125.7 GB RAM · 1,382.5 GB disk | US | In stock | $0.24 | $0.24 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× A1024 vCPU · 62.8 GB RAM · 669.5 GB disk | Netherlands | In stock | $0.24 | $0.24 | 00:00 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× A1024 vCPU · 62.8 GB RAM · 736.4 GB disk | US | In stock | $0.24 | $0.24 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× A1024 vCPU · 62.8 GB RAM · 691.2 GB disk | US | In stock | $0.24 | $0.24 | 00:02 UTCfresh | Receipt |
| LeaderGPUTrust 59 | 10× A10384 GB RAM | LeaderGPU data centres (EU) | In stock | $0.41 | $0.41 | 00:19 UTCfresh | Receipt |
| 1× A10 | Lithuania | Unavailable | $0.49 | $0.49 | 00:19 UTCfresh | Receipt | |
| Vast.aiTrust 78 | 4× A1048 vCPU · 94.2 GB RAM · 177 GB disk | China | In stock | $0.83 | $0.83 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× A1064 vCPU · 125.8 GB RAM · 260 GB disk | China | In stock | $0.83 | $0.83 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× A1024 vCPU · 47.1 GB RAM · 88.5 GB disk | China | In stock | $0.83 | $0.83 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× A1032 vCPU · 62.9 GB RAM · 130 GB disk | China | In stock | $0.83 | $0.83 | 00:03 UTCfresh | Receipt |
| A10 | — | Stock unknown | $1.02 | $1.02 | Oct 25, 2026older reading | Receipt | |
| Prime IntellectTrust 46marketplace floor | A10 PCIE | US | Stock unknown | $1.29 | $1.29 | Sep 29, 2026older reading | Receipt |
| LambdaTrust 80 | 1× A10 | US | Stock unknown | $1.29 | $1.29 | 00:19 UTCfresh | Receipt |
| IONOS | 1× A1032 vCPU · 128 GB RAM · 960 GB disk | — | In stock | $1.35 | $1.35 | 00:23 UTCfresh | Receipt |
 Omega Gradientresold from Sesterce Cloud | 1× A1030 vCPU · 200 GB RAM · 1,400 GB disk | US | In stock | $1.36 | $1.36 | 00:19 UTCfresh | Receipt |
| Omega Gradientresold from Sesterce Cloud | 1× A1030 vCPU · 200 GB RAM · 1,400 GB disk | US | In stock | $1.36 | $1.36 | 00:19 UTCfresh | Receipt |
 GPUNETresold from other clouds (the upstream is named in each offer) | 1× A1030 vCPU · 200 GB RAM · 1,400 GB disk | India · US | In stock | $1.36 | $1.36 | 00:24 UTCfresh | Receipt |
| 1× A1030 vCPU · 200 GB RAM · 1,400 GB disk | US | In stock | $1.42 | $1.42 | 00:19 UTCfresh | Receipt | |
 Volcano Engine | 1× A1014 vCPU · 56 GB RAM | China | Stock unknown | $1.52 | $1.52 | 00:31 UTCfresh | Receipt |
| 1× A1030 vCPU · 200 GB RAM · 1,400 GB disk | daf1e228:dulles-usa-1 | In stock | $1.55 | $1.55 | 00:19 UTCfresh | Receipt |
39 fresh offers · the 25 cheapest shown here, all of them in the comparison tool · 31 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 · hour24 GB | $0.017 | $0.056 |
| per PFLOP FP16 · hour125 TFLOPS | $3.314 | $10.834 |
| per TB/s of bandwidth · hour0.60 TB/s | $0.691 | $2.257 |
| Model | Needs | Smallest config | $ / month |
|---|---|---|---|
| all MiniLM L6 v2Sentence Transformers | 1 GBFP8 | 1× A10at Vast.ai | $167 |
| paraphrase multilingual MiniLM L12 v2Sentence Transformers | 1 GBFP8 | 1× A10at Vast.ai | $167 |
| bge-m3BAAI | 1 GBFP8 | 1× A10at Vast.ai | $167 |
| Qwen3 0.6BQwen | 1 GBFP8 | 1× A10at Vast.ai | $167 |
| all-mpnet-base-v2Sentence Transformers | 1 GBFP8 | 1× A10at Vast.ai | $167 |
| bge-reranker-v2-m3BAAI | 1 GBFP8 | 1× A10at Vast.ai | $167 |
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 →
A10 · comparisons and collectionsCompare the A10 side by side
Questions about renting the A10
How much does the A10 cost per hour?
Today the A10 rents from $0.41 per GPU-hour on-demand, with a median of $1.35 across 9 providers, each counted once at its cheapest current offer (19 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 A10?
13 providers have a current A10 offer in stock. Cheapest first: Vast Ai ($0.23), Leadergpu ($0.41), Tencent Cloud ($1.02), Prime Intellect ($1.29), Lambda ($1.29), Ionos ($1.35). Older readings from other providers stay listed on this page, in grey, and are never ranked.
How much memory does the A10 have?
24 GB of memory at 0.60 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 A10 cheapest right now?
The lowest true cost among eligible offers is $0.41 per GPU-hour at LeaderGPU for a 10-GPU machine in LeaderGPU data centres (EU), 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 A10 cheaper on spot or reserved?
Spot (interruptible) capacity starts at $0.21 per GPU-hour; reserved terms start at $0.37. Spot suits jobs that checkpoint; reserved suits machines that run all month.