priceVerified 2026-06-20Live prices updated just now
L4 GPU cloud prices
NVIDIA L4 is commonly evaluated for LLM inference. A compact 72 W Ada Lovelace inference GPU with 24 GB GDDR6 for cost-efficient, high-density serving.
Cheapest
$0.174/hr
AWS
Median
$1.234/hr
1044 offers
Providers
3
indexed providers
730-hour floor
$127
before extras/taxes
VRAM
24GB
FP16
121 TFLOPS
Bandwidth
300 GB/s
TDP
72W
Cheapest L4 providers
Provider floors from live indexed offers. Lower is better.
Common search intents
L4 priceL4 GPU rentalL4 cloud GPU