Prices Providers Compare

…

© 2026 PetaPrice

Providers GPU comparisons Architectures Price report Glossary FAQ Methodology Corrections JSON API llms.txt Privacy Imprint

Price disclaimer: All prices are indicative list prices in USD, collected automatically from provider APIs and public catalogs and refreshed about every 2 hours. They exclude taxes, storage, egress and other fees unless a provider bundles them, may be out of date, and don't guarantee availability. The provider's own website is authoritative at the time of booking. PetaPrice does not rent out compute and is not a party to any contract with a provider. FLOPS are theoretical peak values from vendor datasheets. More

GPU glossary/Memory

KV cache

Also known as: key-value cache

Memory an LLM keeps for every token in its context during inference. Long contexts and many parallel requests need a lot of it, on top of the model weights.

GPUs with KV cache, best value first

Ranked by $ per GB of VRAM per hour at each GPU's lowest on-demand price.

1Instinct MI325X256 GB$2.00/h$0.008/GB·h
2Instinct MI355X288 GB$2.59/h$0.009/GB·h
3Instinct MI300X192 GB$1.85/h$0.010/GB·h
4Gaudi 296 GB$1.10/h$0.011/GB·h
5RTX PRO 6000 Blackwell96 GB$1.25/h$0.013/GB·h
6A100 SXM 80GB80 GB$1.07/h$0.013/GB·h
7A100 PCIe 80GB80 GB$1.13/h$0.014/GB·h
8H200 SXM141 GB$2.25/h$0.016/GB·h

Compare every GPU →

Related terms

VRAMThe GPU's own memory. The model weights, activations and KV cache must fit in it (or be split across GPUs), so VRAM often decides which GPU you can use at all.
Memory bandwidthHow fast the GPU reads its memory, in GB/s or TB/s. Generating LLM tokens is usually limited by bandwidth rather than FLOPS, which is why PetaPrice can rank GPUs by bandwidth per dollar.

Memory

HBMHigh Bandwidth Memory, stacked next to the chip on datacenter GPUs (HBM2e, HBM3, HBM3e). Several times faster than the GDDR memory on consumer and workstation cards.