Cheapest
Lowest true cost per GPU-hour, in stock or stock unknown, newest reading per provider
Clore.ai1× · Brazil$0.08
Theta EdgeCloud1× · US$0.09- 4
gcube1× · Korea$0.13
Rented today by 4 providers with a current on-demand offer, from $0.06 to $0.22 per GPU-hour, median $0.09. 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 2, 2026 00:32 UTCCheapest true cost, best throughput per dollar, highest Trust Score. One provider per step, ten places, every row dated.







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 | |
|---|---|---|---|---|---|---|---|
| 5× RTX 40604 vCPU · 16 GB RAM · 869.6 GB disk | Türkiye | Unavailable | $0.04 | $0.04 | 00:03 UTCfresh | Receipt | |
| 2× RTX 406012 vCPU · 31.3 GB RAM · 266.3 GB disk | Romania | In stock | $0.06 | $0.06 | 00:03 UTCfresh | Receipt | |
| 1× RTX 40606 vCPU · 15.6 GB RAM · 133.2 GB disk | Romania | In stock | $0.06 | $0.06 | 00:03 UTCfresh | Receipt | |
| 1× RTX 406014 vCPU · 24 GB RAM · 948.941 GB disk | Türkiye | Unavailable | $0.08 | $0.08 | 00:03 UTCfresh | Receipt | |
| 1× RTX 406014 vCPU · 31.4 GB RAM · 316 GB disk | Canada | In stock | $0.08 | $0.08 | 00:00 UTCfresh | Receipt | |
| 2× RTX 406010 vCPU · 31.4 GB RAM · 65.5 GB disk | US | In stock | $0.08 | $0.08 | 00:01 UTCfresh | Receipt | |
| 1× RTX 40605 vCPU · 15.7 GB RAM · 32.7 GB disk | US | In stock | $0.08 | $0.08 | 00:01 UTCfresh | Receipt | |
| 1× RTX 40604 vCPU · 32 GB RAM · 92.484 GB disk | Australia | Unavailable | $0.08 | $0.08 | 00:03 UTCfresh | Receipt | |
| 1× RTX 40608 vCPU · 64 GB RAM · 12.977 GB disk | Brazil | In stock | $0.08 | $0.08 | 00:03 UTCfresh | Receipt | |
| 1× RTX 406028 vCPU · 15.6 GB RAM · 250.9 GB disk | US | In stock | $0.09 | $0.09 | 00:19 UTCfresh | Receipt | |
| 1× RTX 406016 vCPU · 31.5 GB RAM · 1,006.9 GB disk | US | In stock | $0.12 | $0.12 | 00:19 UTCfresh | Receipt | |
| 1× RTX 406012 vCPU · 16 GB RAM · 50 GB disk | Korea | Stock unknown | $0.13 | $0.13 | 00:24 UTCfresh | Receipt | |
| 1× RTX 406024 vCPU · 15.5 GB RAM · 1,006.9 GB disk | US | In stock | $0.14 | $0.14 | 00:19 UTCfresh | Receipt | |
| 1× RTX 40604 vCPU · 16 GB RAM · 33.977 GB disk | US | Unavailable | $0.21 | $0.21 | 00:03 UTCfresh | Receipt | |
| 1× RTX 406012 vCPU · 16 GB RAM · 512 GB disk | Korea | Stock unknown | $0.22 | $0.22 | 00:24 UTCfresh | Receipt | |
| 1× RTX 406012 vCPU · 20 GB RAM · 76 GB disk | Korea | Stock unknown | $0.37 | $0.37 | 00:24 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 · hour8 GB | $0.008 | $0.011 |
| per TB/s of bandwidth · hour0.27 TB/s | $0.225 | $0.321 |
| Model | Needs | Smallest config | $ / month |
|---|---|---|---|
| all MiniLM L6 v2Sentence Transformers | 1 GBFP8 | 1× RTX 4060at Vast.ai | $45 |
| paraphrase multilingual MiniLM L12 v2Sentence Transformers | 1 GBFP8 | 1× RTX 4060at Vast.ai | $45 |
| bge-m3BAAI | 1 GBFP8 | 1× RTX 4060at Vast.ai | $45 |
| Qwen3 0.6BQwen | 1 GBFP8 | 1× RTX 4060at Vast.ai | $45 |
| all-mpnet-base-v2Sentence Transformers | 1 GBFP8 | 1× RTX 4060at Vast.ai | $45 |
| bge-reranker-v2-m3BAAI | 1 GBFP8 | 1× RTX 4060at Vast.ai | $45 |
Today the RTX 4060 rents from $0.06 per GPU-hour on-demand, with a median of $0.09 across 4 providers, each counted once at its cheapest current offer (5 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.
4 providers have a current RTX 4060 offer in stock. Cheapest first: Vast Ai ($0.06), Clore Ai ($0.08), Theta Edgecloud ($0.09), Gcube ($0.13). Older readings from other providers stay listed on this page, in grey, and are never ranked.
8 GB of GDDR6X at 0.27 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 $0.06 per GPU-hour at Vast.ai for a 2-GPU machine in Romania, 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 $0.20. Spot suits jobs that checkpoint; reserved suits machines that run all month.