Ranking 01
Cheapest
Lowest true cost per GPU-hour, in stock or stock unknown, newest reading per provider
Hikube1× · Switzerland$0.27
OpenRelay1× · 00:20 UTC$0.43- 4
JarvisLabs1× · 00:32 UTC$0.44 - 5
GPURento1× · Germany · France$0.44
NVIDIA · Ada Lovelace · Datacenter · 47 providers list itNVIDIA L4 cloud prices
Rented today by 25 providers with a current on-demand offer, from $0.27 to $2.01 per GPU-hour, median $0.80. Every number below links to the page it was read from, with its read date.
Memory24GB
Bandwidth0.30TB/s
FP16 tensor121TFLOPS
FP3230.3TFLOPS
Power72W
Specifications: manufacturer figures.
Cheapest on-demand · read 00:32 UTC
$0.27/ GPU·h
Infomaniak2× L4 · 24 GB · Switzerland- Median
- $0.80 25 providers, once each
- 30 days
- −1.5%
- 90 days
- −2.8%
Prices by rental mode · On-demand · Spot · Reserved · ServerlessL4 prices today
Cheapest, median and spread among current offers. Medians count one floor per marketplace and need at least three offers.
Cheapest$0.27Infomaniak
Median$0.80n = 72
Highest$2.01among current offers
Current offers12025 providers · last 45 days
Ever listed22138 providers on file
Where today's on-demand offers sitone dot per eligible offer (72) · the pool behind the tiles · read Nov 2, 2026 00:32 UTC
Provider offer70Marketplace floor2Median$0.80Middle half$0.76 – $1.07
72 eligible offers from 25 providers, binned every $0.05: from $0.27 (Infomaniak) to $2.01 (AWS). 25 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 · 4 provider lines from their 30-day series · read Nov 2, 2026
Median · all providers$0.80Providers
Today $0.8030 days -1.5%92 days -2.8%Low $0.34 · Oct 12High $1.00 · Aug 8
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 L4 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
Runpod1× · 00:03 UTCValue 18$0.59
UpCloud1× · 00:32 UTCValue 16$0.64- 4
Google Cloud1× · Australia +25Value 13$0.70 - 5
Northflank1× · 00:32 UTCValue 9$0.80
Ranking 03
Most trusted
Highest Trust Score among providers with an eligible offer · unscored providers follow, cheapest first
- Northflank1× · 00:32 UTCTrust 92$0.80
E2E Networks1× · IndiaTrust 87$0.57
- 4
Baseten1× · 00:32 UTCTrust 87$0.85 - 5Google Cloud1× · Australia +25Trust 81$0.70
72 eligible on-demand offers from 25 providers · median $0.80 (n = 72) · not ranked: 11 unavailable, 10 resold, 1 older readings · readings of the last 45 days · reference Nov 2, 2026 · 00:32 UTCRankings are never sponsored. How we rank →
All offers · 636 readings on file · 47 providersEvery L4 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 | |
|---|---|---|---|---|---|---|---|
 Clore.aiTrust 49 | 4× L424 vCPU · 192 GB RAM · 918.303 GB disk | US | Unavailable | $0.10 | $0.10 | 00:03 UTCfresh | Receipt |
 Vast.aiTrust 78marketplace flooroutlier · suspended | 1× L432 vCPU · 18.9 GB RAM · 318 GB disk | Japan | In stock | $0.10 | $0.10 | 00:00 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× L420 vCPU · 21.9 GB RAM · 314 GB disk | Malaysia | In stock | $0.10 | $0.10 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× L416 vCPU · 21.3 GB RAM · 316.9 GB disk | Malaysia | In stock | $0.10 | $0.10 | 00:01 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× L424 vCPU · 15.2 GB RAM · 320.9 GB disk | Japan | In stock | $0.10 | $0.10 | 00:03 UTCfresh | Receipt |
 Edgevanamarketplace flooroutlier · suspended | 1× L420 vCPU · 22 GB RAM · 314 GB disk | Malaysia | In stock | $0.12 | $0.12 | 00:21 UTCfresh | Receipt |
| Infomaniak | 2× L48 vCPU · 16 GB RAM | Switzerland | Stock unknown | $0.27 | $0.27 | 00:24 UTCfresh | Receipt |
| Infomaniak | 4× L416 vCPU · 32 GB RAM | Switzerland | Stock unknown | $0.27 | $0.27 | 00:24 UTCfresh | Receipt |
| Hikube | 1× L4 | Switzerland | Stock unknown | $0.27 | $0.27 | 00:23 UTCfresh | Receipt |
| Infomaniak | 1× L44 vCPU · 8 GB RAM · 50 GB disk | Switzerland | Stock unknown | $0.28 | $0.28 | 00:24 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× L412 vCPU · 23.5 GB RAM · 387 GB disk | Brazil | In stock | $0.34 | $0.34 | 00:01 UTCfresh | Receipt |
| OpenRelay | 1× L4 | — | Stock unknown | $0.43 | $0.43 | 00:20 UTCfresh | Receipt |
| GPURento | 1× L4 | Germany · France | Stock unknown | $0.44 | $0.44 | 00:25 UTCfresh | Receipt |
| JarvisLabsTrust 49 | 1× L4 | — | Stock unknown | $0.44 | $0.44 | 00:32 UTCfresh | Receipt |
| Vast.aiTrust 78 | 4× L4102.4 vCPU · 100.5 GB RAM · 1,108 GB disk | US | In stock | $0.49 | $0.49 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× L414 vCPU · 23.4 GB RAM · 429 GB disk | US | In stock | $0.50 | $0.50 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× L442.666666666666664 vCPU · 57.6 GB RAM · 416.7 GB disk | US | In stock | $0.50 | $0.50 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 2× L451.2 vCPU · 50.2 GB RAM · 554 GB disk | US | In stock | $0.50 | $0.50 | 00:03 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× L421.333333333333332 vCPU · 28.8 GB RAM · 208.3 GB disk | US | In stock | $0.50 | $0.50 | 00:02 UTCfresh | Receipt |
| Vast.aiTrust 78 | 1× L425.6 vCPU · 25.1 GB RAM · 277 GB disk | US | In stock | $0.50 | $0.50 | 00:03 UTCfresh | Receipt |
| OpenRelay | 1× L4 | — | Stock unknown | $0.55 | $0.55 | 00:20 UTCfresh | Receipt |
| 1× L425 vCPU · 110 GB RAM | India | Stock unknown | $0.57 | $0.57 | 00:19 UTCfresh | Receipt | |
| RunpodTrust 95 | 1× L4 | 3 datacenter(s): EU-RO-1 (low) | In stock | $0.59 | $0.59 | 00:03 UTCfresh | Receipt |
| UpCloudTrust 75 | 1× L4 | — | Stock unknown | $0.64 | $0.64 | 00:32 UTCfresh | Receipt |
| UpCloudTrust 75 | 2× L4 | — | Stock unknown | $0.65 | $0.65 | 00:32 UTCfresh | Receipt |
120 fresh offers · the 25 cheapest shown here, all of them in the comparison tool · 101 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 | $0.011 | $0.034 |
| per PFLOP FP16 · hour121 TFLOPS | $2.250 | $6.651 |
| per TB/s of bandwidth · hour0.30 TB/s | $0.908 | $2.683 |
| Model | Needs | Smallest config | $ / month |
|---|---|---|---|
| all MiniLM L6 v2Sentence Transformers | 1 GBFP8 | 1× L4at Vast.ai | $76 |
| paraphrase multilingual MiniLM L12 v2Sentence Transformers | 1 GBFP8 | 1× L4at Vast.ai | $76 |
| bge-m3BAAI | 1 GBFP8 | 1× L4at Vast.ai | $76 |
| Qwen3 0.6BQwen | 1 GBFP8 | 1× L4at Vast.ai | $76 |
| all-mpnet-base-v2Sentence Transformers | 1 GBFP8 | 1× L4at Vast.ai | $76 |
| bge-reranker-v2-m3BAAI | 1 GBFP8 | 1× L4at Vast.ai | $76 |
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 →
L4 · comparisons and collectionsCompare the L4 side by side
Side by side
Collections
Questions about renting the L4
How much does the L4 cost per hour?
Today the L4 rents from $0.27 per GPU-hour on-demand, with a median of $0.80 across 25 providers, each counted once at its cheapest current offer (72 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 L4?
31 providers have a current L4 offer in stock. Cheapest first: Vast Ai ($0.10), Edgevana ($0.12), Infomaniak ($0.27), Hikube ($0.27), Openrelay ($0.43), Gpurento ($0.44). Older readings from other providers stay listed on this page, in grey, and are never ranked.
How much memory does the L4 have?
24 GB of memory at 0.30 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 L4 cheapest right now?
The lowest true cost among eligible offers is $0.27 per GPU-hour at Infomaniak for a 2-GPU machine in Switzerland, 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 L4 cheaper on spot or reserved?
Spot (interruptible) capacity starts at $0.10 per GPU-hour; reserved terms start at $0.32. Spot suits jobs that checkpoint; reserved suits machines that run all month.