GPU Price Index
Language / English

Best cloud GPU for Llama 3.1 70B LLM inference (FP16)

Compare whole-GPU quotes for Llama 3.1 70B. “Best” means the lowest instance bill among reviewed GPU models where one GPU passes the cited memory estimate and software floor in this snapshot; a tensor-parallel multi-GPU instance is chosen only when no single GPU fits, and cheaper tensor-parallel options are listed separately. Throughput and successful execution have not been benchmarked.

Only current whole-GPU on-demand and Spot USD quotes in standard or unspecified regions qualify. Fractional GPUs, GPU-component prices, promotional “from” prices, tax-included quotes and explicit out-of-stock records are excluded. Quotes with unknown tax basis remain labelled; tier B/C quotes are display-only.

Minimum VRAM screening rule

Labelled estimate, batch 1: 70B parameters × 2 bytes/parameter = 140 GB weights; required = 140 × 1.2 + 2.684 GB FP16 KV cache at 8192 tokens = 170.684 GB.

Hugging Face Accelerate says inference may need up to about 20% extra memory beyond loading weights. We use that guidance as the 1.2 allowance, then add the stated KV cache. This is our estimate, not a runtime requirement published by the model developer; kernels, context, batches and backend can change usage.

KV input: 2 × 80 layers × 8 KV heads × head dimension 128 × 2 bytes × 8192 tokens / 10⁹ = 2.684 GB, batch 1.

The blog provides rounded KV values; this screen instead uses the model architecture formula above, in decimal GB.

Tensor-parallel inputs: 64 attention heads and 8 KV heads; GPU count must divide both.

Reviewed software floor: vLLM on Linux, NVIDIA CUDA compute capability ≥ 7.5; or AMD MI200s (gfx90a), MI300 (gfx942), MI350 (gfx950), Radeon RX 7900 series (gfx1100/1101), Radeon RX 9000 series (gfx1200/1201), Ryzen AI MAX / AI 300 Series (gfx1151/1150). ROCm ≥ 6.3; MI350 ≥ 7.0; Ryzen ≥ 7.0.2. Architecture eligibility does not certify a particular quantization kernel or host wheel. On aarch64, stable PyTorch wheels target only 8.0/9.0/10.0/11.0/12.0; T4G (CC 7.5) is memory-only. AMD Arm hosts are outside this screen.

Capacity comes only from reviewed per-model manufacturer specifications linked in each row. Decimal GB estimates are compared conservatively with those published capacity labels, without credit for a possible GiB interpretation. Unreviewed models (listed below), over-reported capacities, mining SKUs and laptop GPUs are omitted. One-GPU fits and tensor-parallel instance fits are screened separately.

Price observations dated: 2026-11-18

Qualifying current listings: 429. Distinct model/type minima shown: 63.

“Best” on this page

On-demand: B200 SXM6 180GB · Verda / DataCrunch · 1 GPU per instance · $9.80 per instance-hour

Spot: B200 SXM6 180GB · Verda / DataCrunch · 1 GPU per instance · $4.90 per instance-hour

One GPU’s memory is enough: cheapest instance

On-demand: B200 SXM6 180GB · Verda / DataCrunch · 1 GPU per instance · $9.80 per instance-hour

Spot: B200 SXM6 180GB · Verda / DataCrunch · 1 GPU per instance · $4.90 per instance-hour

Cheapest multi-GPU instance

On-demand: RTX A5000 24GB · Clore.ai · 8 GPUs per instance · $1.13 per instance-hour

Spot: H100 NVL 94GB · Clore.ai · 2 GPUs per instance · $0.917 per instance-hour

One-GPU fit tables show each model/type’s cheapest per-GPU quote; equal rates prefer a smaller instance bill, then fewer GPUs. Tensor-parallel tables rank by instance-hour bill. Headlines use the cheapest qualifying instance bill. Regions, providers, allocations and tax bases may differ; these are independent minima, not matched Spot discounts. Quote cards retain billing and availability conditions.

Not yet reviewed — memory unverified (model names only)

A100PCIE40GB · B300 HGX · B300 SXM · CMP 170HX · CMP 30HX · CMP 40HX · CMP 50HX · CMP 70HX · CMP 90HX · GTX 1050 Ti · GTX 1650 · GTX 970 · GeForce GTX 1060 · GeForce GTX 1070 · GeForce GTX 1080 Ti · K40 · P100 · P104-100 · P106-100 · P4 · Quadro P2200 · Quadro-RTX5000 · RTX 2060 · RTX 3050 Laptop GPU · RTX 3050 Ti Laptop GPU · RTX 3060 Laptop GPU · RTX 3070 Laptop GPU · RTX 4090 Laptop GPU · RTX 5090 Laptop GPU · RTX A5500 Laptop GPU · RTX PRO 4000 Blackwell SFF Edition · RTX PRO 5000 72GB Blackwell · RTX PRO 6000 Blackwell Max-Q · Radeon Pro V710 · Tesla P4 · Tesla V100S

Fits on one GPU

USD per GPU-hour and per instance-hour; initial billing minimum in the quote cards
GPU modelReviewed GB per GPUPrice typePer GPU $/hrGPUs per instanceInstance $/hrEstimated headroom (single: per GPU; multi: total)Reviewed architecture and checks
MI300X 192GB192Spot$1.118$8.87tight < 1.25× (estimate)AMD · CDNA 3 · gfx942 · non-CUDA · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs
B200 SXM6 180GB180Spot$4.904$19.59tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 10.0 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs
B200 CC SXM6 180GB180Spot$5.004$19.98tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 10.0 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs
MI300X 192GB192On-demand$6.008$48.00tight < 1.25× (estimate)AMD · CDNA 3 · gfx942 · non-CUDA · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs
B300 SXM6 268GB268Spot$6.391$6.39comfortable (estimate)NVIDIA · Blackwell · CUDA CC 10.3
B300 CC SXM6 268GB268Spot$6.524$26.09comfortable (estimate)NVIDIA · Blackwell · CUDA CC 10.3 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs
B200 SXM6 180GB180On-demand$9.792$19.59tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 10.0 · one GPU’s memory passes, but this offer is sold only as an instance with 2 GPUs
B200 CC SXM6 180GB180On-demand$9.992$19.98tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 10.0 · one GPU’s memory passes, but this offer is sold only as an instance with 2 GPUs
B300 SXM6 268GB268On-demand$12.798$102.30comfortable (estimate)NVIDIA · Blackwell · CUDA CC 10.3 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs
B300 CC SXM6 268GB268On-demand$13.044$52.18comfortable (estimate)NVIDIA · Blackwell · CUDA CC 10.3 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs
B200 180GB180On-demand$14.008$112.00tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 10.0 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs
B200 179GB179On-demand$14.248$113.93tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 10.0 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs
B300 268GB268On-demand$17.808$142.42comfortable (estimate)NVIDIA · Blackwell · CUDA CC 10.3 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs

Multi-GPU instances (tensor parallel)

Use 2, 4 or 8 GPUs in one eligible instance. The count must divide both attention and KV heads, and count × reviewed per-GPU GB must meet the estimate. This is a capacity screen; tensor-parallel execution and interconnect must be checked.

USD per GPU-hour and per instance-hour; initial billing minimum in the quote cards
GPU modelReviewed GB per GPUPrice typePer GPU $/hrGPUs per instanceInstance $/hrEstimated headroom (single: per GPU; multi: total)Reviewed architecture and checks
H100 NVL 94GB94Spot$0.4582$0.917tight < 1.25× (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
RTX A5000 24GB24On-demand$0.1428$1.13tight < 1.25× (estimate)NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX A5000 24GB24Spot$0.1428$1.13tight < 1.25× (estimate)NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H100 NVL 94GB94On-demand$0.8332$1.67tight < 1.25× (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
RTX A6000 48GB48Spot$0.4584$1.83tight < 1.25× (estimate)NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
RTX 3090 24GB24On-demand$0.2608$2.08tight < 1.25× (estimate)NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX 3090 24GB24Spot$0.2608$2.08tight < 1.25× (estimate)NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX A6000 48GB48On-demand$0.5504$2.20tight < 1.25× (estimate)NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
A30 24GB24On-demand$0.3508$2.80tight < 1.25× (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 96GB96Spot$1.462$2.92tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
RTX 6000 Ada 48GB48On-demand$0.7904$3.16tight < 1.25× (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
RTX 6000 Ada 48GB48Spot$0.8274$3.31tight < 1.25× (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 Blackwell Workstation 96GB96On-demand$1.672$3.33tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 Blackwell Workstation 96GB96Spot$1.672$3.33tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
L40 48GB48On-demand$0.8604$3.44tight < 1.25× (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect · PCIe only, no NVLink; vLLM suggests pipeline parallelism
RTX A6000 48GB48Spot$0.4588$3.66comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
L40S 48GB48On-demand$0.9704$3.88tight < 1.25× (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect · PCIe only, no NVLink; vLLM suggests pipeline parallelism
L40S 48GB48Spot$1.044$4.16tight < 1.25× (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect · PCIe only, no NVLink; vLLM suggests pipeline parallelism
RTX PRO 6000 Blackwell 96GB96On-demand$2.192$4.38tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
RTX A6000 48GB48On-demand$0.5508$4.40comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
A100 SXM4 80GB80Spot$1.214$4.84comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
RTX 5090 32GB32On-demand$0.6258$5.00comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX 5090 32GB32Spot$0.6258$5.00comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
A100 80GB80On-demand$1.354$5.40comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 96GB96On-demand$2.922$5.84tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 96GB96Spot$1.464$5.84comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
A100 40GB40Spot$0.7388$5.90comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H100 NVL94On-demand$3.112$6.22tight < 1.25× (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
RTX 4090 24GB24On-demand$0.7818$6.25tight < 1.25× (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX 4090 24GB24Spot$0.7818$6.25tight < 1.25× (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX 6000 Ada 48GB48On-demand$0.7908$6.32comfortable (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX 6000 Ada 48GB48Spot$0.8278$6.62comfortable (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
A100 80GB80Spot$0.8598$6.87comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H200 SXM5 141GB141Spot$3.452$6.90comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
L4 24GB24On-demand$0.8658$6.92tight < 1.25× (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect · PCIe only, no NVLink; vLLM suggests pipeline parallelism
A100 SXM4 40GB40Spot$0.8678$6.93comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H200 NVL 141GB141On-demand$3.622$7.24comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 4500 Blackwell 32GB32On-demand$0.9208$7.36comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 Blackwell MaxQ Works 96GB96On-demand$1.884$7.50comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 Blackwell MaxQ Works 96GB96Spot$1.884$7.50comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
L40S 48GB48On-demand$0.9708$7.76comfortable (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect · PCIe only, no NVLink; vLLM suggests pipeline parallelism
RTX PRO 6000 Blackwell Server Edition 96GB96On-demand$4.142$8.29tight < 1.25× (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
L40S 48GB48Spot$1.048$8.32comfortable (estimate)NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect · PCIe only, no NVLink; vLLM suggests pipeline parallelism
RTX PRO 6000 Blackwell 96GB96On-demand$2.194$8.76comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
A100 SXM4 80GB80On-demand$2.424$9.69comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
A100 SXM4 80GB80Spot$1.218$9.69comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H100 SXM 80GB80Spot$2.704$10.80comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
A100 80GB80On-demand$1.358$10.80comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H100 80GB80On-demand$2.734$10.92comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
A100 SXM4 80GB80On-demand$1.388$11.04comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
DGX A100 80GB80On-demand$1.388$11.04comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H100 NVL 94GB94On-demand$2.924$11.68comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 96GB96On-demand$2.924$11.69comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 96GB96Spot$1.468$11.69comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H100 NVL94On-demand$3.114$12.44comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
H200 SXM5 141GB141On-demand$6.912$13.81comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect
H200 SXM5 141GB141Spot$3.454$13.81comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
A100 SXM4 40GB40On-demand$1.738$13.86comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H100 SXM 80GB80On-demand$3.514$14.03comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
H200 NVL 141GB141On-demand$3.624$14.48comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
A10G 24GB24On-demand$2.048$16.29tight < 1.25× (estimate)NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect · PCIe only, no NVLink; vLLM suggests pipeline parallelism
RTX PRO 6000 Blackwell Server Edition 96GB96On-demand$4.144$16.57comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 Blackwell 96GB96On-demand$2.198$17.52comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
A100 NVSwitch 80GB80On-demand$4.534$18.11comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
H100 SXM 80GB80Spot$2.278$18.17comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
A100 40GB40On-demand$2.748$21.96comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H100 NVL 94GB94On-demand$2.928$23.36comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 96GB96On-demand$2.928$23.38comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H100 NVL94On-demand$3.118$24.88comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H100 SXM 80GB80On-demand$3.148$25.12comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H200 SXM5 141GB141On-demand$6.914$27.62comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect
H200 SXM5 141GB141Spot$3.458$27.62comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 4500 32GB32On-demand$3.568$28.51comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H200 NVL 141GB141On-demand$3.628$28.96comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
A100 NVSwitch 40GB40On-demand$3.918$31.30comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
RTX PRO 6000 Blackwell Server Edition 96GB96On-demand$4.148$33.14comfortable (estimate)NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
A100 NVSwitch 80GB80On-demand$4.538$36.22comfortable (estimate)NVIDIA · Ampere · CUDA CC 8.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H200 141GB141On-demand$5.778$46.15comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H100 80GB80On-demand$6.888$55.04comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H200 SXM5 141GB141On-demand$6.908$55.23comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect
H200 141GB141Spot$10.608$84.80comfortable (estimate)NVIDIA · Hopper · CUDA CC 9.0 · tensor parallel across 8 GPUs; needs a serving engine with TP support; check the interconnect

Meets memory only, check software support

USD per GPU-hour and per instance-hour; initial billing minimum in the quote cards
GPU modelReviewed GB per GPUPrice typePer GPU $/hrGPUs per instanceInstance $/hrEstimated headroom (single: per GPU; multi: total)Reviewed architecture and checks
GB300 SXM6 288GB288Spot$7.351$7.35comfortable (estimate)NVIDIA · Blackwell · CUDA CC 10.3 · Arm (aarch64) host · below floor
GB300 SXM6 288GB288On-demand$14.714$58.83comfortable (estimate)NVIDIA · Blackwell · CUDA CC 10.3 · Arm (aarch64) host · below floor

The qualifying model/type sets in Fits on one GPU match the stricter page “Best cloud GPU for Qwen2.5 72B Instruct LLM inference (FP16)”. That page is the cluster’s reference; this page is noindex and omitted from sitemaps.

H100 NVL 94GB 2×

Clore.aiSpotTax unknownA · Official APICommunity marketplace

US

USD (stablecoin) • platform fees may apply

USD $0.917/hr

$0.458 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $0.917/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 122309 · Availability: Available · A · Official API

Reported GPU name: NVIDIA H100 NVL

Reported VRAM: 94 GB

Hourly amount in source scope: USD $0.917/hr · Instance
Source billing unit: Instance-hour
72/72
512 GB
94 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX A5000 24GB 8×

Clore.aiOn-demandTax unknownA · Official APICommunity marketplace

ES

USD (stablecoin) • platform fees may apply

USD $1.13/hr

$0.142 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $1.13/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 124560 · Availability: Available · A · Official API

Reported GPU name: NVIDIA RTX A5000

Reported VRAM: 24 GB

Hourly amount in source scope: USD $1.13/hr · Instance
Source billing unit: Instance-hour
32/64
256 GB
24 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX A5000 24GB 8×

Clore.aiSpotTax unknownA · Official APICommunity marketplace

ES

USD (stablecoin) • platform fees may apply

USD $1.13/hr

$0.142 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $1.13/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 124560 · Availability: Available · A · Official API

Reported GPU name: NVIDIA RTX A5000

Reported VRAM: 24 GB

Hourly amount in source scope: USD $1.13/hr · Instance
Source billing unit: Instance-hour
32/64
256 GB
24 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

H100 NVL 94GB 2×

Clore.aiOn-demandTax unknownA · Official APICommunity marketplace

US

USD (stablecoin) • platform fees may apply

USD $1.67/hr

$0.833 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $1.67/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 122309 · Availability: Available · A · Official API

Reported GPU name: NVIDIA H100 NVL

Reported VRAM: 94 GB

Hourly amount in source scope: USD $1.67/hr · Instance
Source billing unit: Instance-hour
72/72
512 GB
94 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX A6000 48GB 4×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $1.83/hr

$0.458 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $1.83/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4A6000.40V · Availability: Unknown · A · Official API

Reported GPU name: 4x RTX A6000 48GB

Reported VRAM: 192GB GPU RAM

Hourly amount in source scope: USD $1.83/hr · Instance
Source billing unit: Instance-hour
40 CPU
240GB RAM
192GB GPU RAM

API record page

RTX 3090 24GB 8×

Clore.aiOn-demandTax unknownA · Official APICommunity marketplace

HR

USD (stablecoin) • platform fees may apply

USD $2.08/hr

$0.260 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $2.08/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 103366 · Availability: Available · A · Official API

Reported GPU name: NVIDIA GeForce RTX 3090

Reported VRAM: 24 GB

Hourly amount in source scope: USD $2.08/hr · Instance
Source billing unit: Instance-hour
4/4
16 GB
24 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX 3090 24GB 8×

Clore.aiSpotTax unknownA · Official APICommunity marketplace

HR

USD (stablecoin) • platform fees may apply

USD $2.08/hr

$0.260 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $2.08/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 103366 · Availability: Available · A · Official API

Reported GPU name: NVIDIA GeForce RTX 3090

Reported VRAM: 24 GB

Hourly amount in source scope: USD $2.08/hr · Instance
Source billing unit: Instance-hour
4/4
16 GB
24 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX A6000 48GB 4×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 30

Region not specified by provider

USD $2.20/hr

$0.550 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $2.20/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: RTX A6000 (48GB) [ALT Config] | 4 GPU | 1024 storage · Availability: Unknown · C · Display only

Reported GPU name: RTX A6000 (48GB) [ALT Config]

Reported VRAM: 48GB

Hourly amount in source scope: USD $2.20/hr · Instance
Source billing unit: Instance-hour
96 GB
48GB

API record page

A30 24GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 94

Region not specified by provider

USD $2.80/hr

$0.350 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $2.80/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: A30 (24GB) | 8 GPU | 2048 storage · Availability: Unknown · C · Display only

Reported GPU name: A30 (24GB)

Reported VRAM: 24GB

Hourly amount in source scope: USD $2.80/hr · Instance
Source billing unit: Instance-hour
384 GB
24GB

API record page

RTX PRO 6000 96GB 2×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $2.92/hr

$1.46 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $2.92/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 2RTXPRO6000.60V · Availability: Unknown · A · Official API

Reported GPU name: 2x RTX PRO 6000 96GB

Reported VRAM: 192GB GPU RAM

Hourly amount in source scope: USD $2.92/hr · Instance
Source billing unit: Instance-hour
60 CPU
180GB RAM
192GB GPU RAM

API record page

RTX 6000 Ada 48GB 4×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 52

Region not specified by provider

USD $3.16/hr

$0.790 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $3.16/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: RTX 6000 ADA (48GB) | 4 GPU | 1400 storage · Availability: Unknown · C · Display only

Reported GPU name: RTX 6000 ADA (48GB)

Reported VRAM: 48GB

Hourly amount in source scope: USD $3.16/hr · Instance
Source billing unit: Instance-hour
288 GB
48GB

API record page

RTX 6000 Ada 48GB 4×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $3.31/hr

$0.827 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $3.31/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4RTX6000ADA.40V · Availability: Unknown · A · Official API

Reported GPU name: 4x RTX 6000 Ada 48GB

Reported VRAM: 192GB GPU RAM

Hourly amount in source scope: USD $3.31/hr · Instance
Source billing unit: Instance-hour
40 CPU
240GB RAM
192GB GPU RAM

API record page

RTX PRO 6000 Blackwell Workstation 96GB 2×

Clore.aiOn-demandTax unknownA · Official APICommunity marketplace

US

USD (stablecoin) • platform fees may apply

USD $3.33/hr

$1.67 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $3.33/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 121985 · Availability: Available · A · Official API

Reported GPU name: NVIDIA RTX PRO 6000 Blackwell Workstation

Reported VRAM: 96 GB

Hourly amount in source scope: USD $3.33/hr · Instance
Source billing unit: Instance-hour
32/64
128 GB
96 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX PRO 6000 Blackwell Workstation 96GB 2×

Clore.aiSpotTax unknownA · Official APICommunity marketplace

US

USD (stablecoin) • platform fees may apply

USD $3.33/hr

$1.67 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $3.33/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 121985 · Availability: Available · A · Official API

Reported GPU name: NVIDIA RTX PRO 6000 Blackwell Workstation

Reported VRAM: 96 GB

Hourly amount in source scope: USD $3.33/hr · Instance
Source billing unit: Instance-hour
32/64
128 GB
96 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

L40 48GB 4×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 50

Region not specified by provider

USD $3.44/hr

$0.860 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $3.44/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: L40 (48GB) | 4 GPU | 2500 storage · Availability: Unknown · C · Display only

Reported GPU name: L40 (48GB)

Reported VRAM: 48GB

Hourly amount in source scope: USD $3.44/hr · Instance
Source billing unit: Instance-hour
288 GB
48GB

API record page

RTX A6000 48GB 8×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $3.66/hr

$0.458 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $3.66/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 8A6000.80V · Availability: Unknown · A · Official API

Reported GPU name: 8x RTX A6000 48GB

Reported VRAM: 384GB GPU RAM

Hourly amount in source scope: USD $3.66/hr · Instance
Source billing unit: Instance-hour
80 CPU
480GB RAM
384GB GPU RAM

API record page

L40S 48GB 4×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 46

Region not specified by provider

USD $3.88/hr

$0.970 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $3.88/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: L40S (48GB) | 4 GPU | 2500 storage · Availability: Unknown · C · Display only

Reported GPU name: L40S (48GB)

Reported VRAM: 48GB

Hourly amount in source scope: USD $3.88/hr · Instance
Source billing unit: Instance-hour
288 GB
48GB

API record page

L40S 48GB 4×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $4.16/hr

$1.04 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $4.16/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4L40S.80V · Availability: Unknown · A · Official API

Reported GPU name: 4x L40S 48GB

Reported VRAM: 192GB GPU RAM

Hourly amount in source scope: USD $4.16/hr · Instance
Source billing unit: Instance-hour
80 CPU
240GB RAM
192GB GPU RAM

API record page

RTX PRO 6000 Blackwell 96GB 2×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 30

Region not specified by provider

USD $4.38/hr

$2.19 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $4.38/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: RTX PRO 6000 Blackwell (96GB) [Reduced Storage] | 2 GPU | 700 storage · Availability: Unknown · C · Display only

Reported GPU name: RTX PRO 6000 Blackwell (96GB) [Reduced Storage]

Reported VRAM: 96GB

Hourly amount in source scope: USD $4.38/hr · Instance
Source billing unit: Instance-hour
288 GB
96GB

API record page

RTX A6000 48GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 62

Region not specified by provider

USD $4.40/hr

$0.550 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $4.40/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: RTX A6000 (48GB) [ALT Config] | 8 GPU | 2048 storage · Availability: Unknown · C · Display only

Reported GPU name: RTX A6000 (48GB) [ALT Config]

Reported VRAM: 48GB

Hourly amount in source scope: USD $4.40/hr · Instance
Source billing unit: Instance-hour
192 GB
48GB

API record page

A100 SXM4 80GB 4×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $4.84/hr

$1.21 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $4.84/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4A100.88V · Availability: Unknown · A · Official API

Reported GPU name: 4x A100 SXM4 80GB

Reported VRAM: 320GB GPU RAM

Hourly amount in source scope: USD $4.84/hr · Instance
Source billing unit: Instance-hour
88 CPU
480GB RAM
320GB GPU RAM

API record page

B200 SXM6 180GB 1×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $4.90/hr

$4.90 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $4.90/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 1B200.30V · Availability: Unknown · A · Official API

Reported GPU name: 1x B200 SXM6 180GB

Reported VRAM: 180GB GPU RAM

Hourly amount in source scope: USD $4.90/hr · Instance
Source billing unit: Instance-hour
30 CPU
170GB RAM
180GB GPU RAM

API record page

RTX 5090 32GB 8×

Clore.aiOn-demandTax unknownA · Official APICommunity marketplace

BY

USD (stablecoin) • platform fees may apply

USD $5.00/hr

$0.625 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $5.00/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 85081 · Availability: Available · A · Official API

Reported GPU name: NVIDIA GeForce RTX 5090

Reported VRAM: 32 GB

Hourly amount in source scope: USD $5.00/hr · Instance
Source billing unit: Instance-hour
48/96
256 GB
32 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX 5090 32GB 8×

Clore.aiSpotTax unknownA · Official APICommunity marketplace

BY

USD (stablecoin) • platform fees may apply

USD $5.00/hr

$0.625 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $5.00/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 85081 · Availability: Available · A · Official API

Reported GPU name: NVIDIA GeForce RTX 5090

Reported VRAM: 32 GB

Hourly amount in source scope: USD $5.00/hr · Instance
Source billing unit: Instance-hour
48/96
256 GB
32 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

A100 80GB 4×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 60

Region not specified by provider

USD $5.40/hr

$1.35 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $5.40/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: A100 (80GB) | 4 GPU | 2048 storage · Availability: Unknown · C · Display only

Reported GPU name: A100 (80GB)

Reported VRAM: 80GB

Hourly amount in source scope: USD $5.40/hr · Instance
Source billing unit: Instance-hour
300 GB
80GB

API record page

RTX PRO 6000 96GB 2×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $5.84/hr

$2.92 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $5.84/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 2RTXPRO6000.60V · Availability: Unknown · A · Official API

Reported GPU name: 2x RTX PRO 6000 96GB

Reported VRAM: 192GB GPU RAM

Hourly amount in source scope: USD $5.84/hr · Instance
Source billing unit: Instance-hour
60 CPU
180GB RAM
192GB GPU RAM

API record page

RTX PRO 6000 96GB 4×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $5.84/hr

$1.46 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $5.84/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4RTXPRO6000.120V · Availability: Unknown · A · Official API

Reported GPU name: 4x RTX PRO 6000 96GB

Reported VRAM: 384GB GPU RAM

Hourly amount in source scope: USD $5.84/hr · Instance
Source billing unit: Instance-hour
120 CPU
360GB RAM
384GB GPU RAM

API record page

A100 40GB 8×

AzureSpotTax unknownA · Official API

vCPU: 96 · RAM (GiB): 900

eastus

USD $5.90/hr

$0.738 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $5.90/hr · Minimum billing duration unknown

View on Azure →All offers →
Details & source

SKU: Standard_ND96asr_v4 · Availability: Unknown · A · Official API

Reported GPU name: A100 40GB

Hourly amount in source scope: USD $5.90/hr · Instance
Source billing unit: Instance-hour

API record page

H100 NVL 2×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 36

Region not specified by provider

USD $6.22/hr

$3.11 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $6.22/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: H100 NVL | 2 GPU | 1500 storage · Availability: Unknown · C · Display only

Reported GPU name: H100 NVL

Hourly amount in source scope: USD $6.22/hr · Instance
Source billing unit: Instance-hour
256 GB

API record page

RTX 4090 24GB 8×

Clore.aiOn-demandTax unknownA · Official APICommunity marketplace

HR

USD (stablecoin) • platform fees may apply

USD $6.25/hr

$0.781 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $6.25/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 87636 · Availability: Available · A · Official API

Reported GPU name: NVIDIA GeForce RTX 4090

Reported VRAM: 24 GB

Hourly amount in source scope: USD $6.25/hr · Instance
Source billing unit: Instance-hour
4/4
16 GB
24 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX 4090 24GB 8×

Clore.aiSpotTax unknownA · Official APICommunity marketplace

HR

USD (stablecoin) • platform fees may apply

USD $6.25/hr

$0.781 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $6.25/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 87636 · Availability: Available · A · Official API

Reported GPU name: NVIDIA GeForce RTX 4090

Reported VRAM: 24 GB

Hourly amount in source scope: USD $6.25/hr · Instance
Source billing unit: Instance-hour
4/4
16 GB
24 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX 6000 Ada 48GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 104

Region not specified by provider

USD $6.32/hr

$0.790 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $6.32/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: RTX 6000 ADA (48GB) | 8 GPU | 2800 storage · Availability: Unknown · C · Display only

Reported GPU name: RTX 6000 ADA (48GB)

Reported VRAM: 48GB

Hourly amount in source scope: USD $6.32/hr · Instance
Source billing unit: Instance-hour
640 GB
48GB

API record page

B300 SXM6 268GB 1×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $6.39/hr

$6.39 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $6.39/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 1B300.30V · Availability: Unknown · A · Official API

Reported GPU name: 1x B300 SXM6 268GB

Reported VRAM: 268GB GPU RAM

Hourly amount in source scope: USD $6.39/hr · Instance
Source billing unit: Instance-hour
30 CPU
255GB RAM
268GB GPU RAM

API record page

RTX 6000 Ada 48GB 8×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $6.62/hr

$0.827 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $6.62/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 8RTX6000ADA.80V · Availability: Unknown · A · Official API

Reported GPU name: 8x RTX 6000 Ada 48GB

Reported VRAM: 384GB GPU RAM

Hourly amount in source scope: USD $6.62/hr · Instance
Source billing unit: Instance-hour
80 CPU
480GB RAM
384GB GPU RAM

API record page

A100 80GB 8×

AzureSpotTax unknownA · Official API

vCPU: 96 · RAM (GiB): 1900

centralus

USD $6.87/hr

$0.859 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $6.87/hr · Minimum billing duration unknown

View on Azure →All offers →
Details & source

SKU: Standard_ND96amsr_A100_v4 · Availability: Unknown · A · Official API

Reported GPU name: A100 80GB

Hourly amount in source scope: USD $6.87/hr · Instance
Source billing unit: Instance-hour

API record page

H200 SXM5 141GB 2×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $6.90/hr

$3.45 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $6.90/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 2H200.141S.88V · Availability: Unknown · A · Official API

Reported GPU name: 2x H200 SXM5 141GB

Reported VRAM: 282GB GPU RAM

Hourly amount in source scope: USD $6.90/hr · Instance
Source billing unit: Instance-hour
88 CPU
340GB RAM
282GB GPU RAM

API record page

L4 24GB 8×

ScalewayOn-demandTax excludedA · Official API

vCPU: 64 · RAM (GiB): 384

fr-par-1

USD $6.92/hr

$0.865 per GPU-hour

per instance-hour · checked

Original hourly price: EUR 6.3/hr · Instance

Minimum billable instance cost: USD $6.92/hr · Minimum billing duration unknown

View on Scaleway →All offers →
Details & source

SKU: /instance/server/l4_8_24g/fr-par-1 · Availability: Unknown · A · Official API

Reported GPU name: L4

Hourly amount in source scope: USD $6.92/hr · Instance
Source billing unit: Instance-minute
Original hourly price: EUR 6.3 · USD conversion rate: 1.0989 · ECB 2026-11-17
AMD EPYC 7413 (2.65 GHz), x64, vCPUs: 64
384 GiB

API record page

A100 SXM4 40GB 8×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $6.93/hr

$0.867 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $6.93/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 8A100.40S.176V · Availability: Unknown · A · Official API

Reported GPU name: 8x A100 SXM4 40GB

Reported VRAM: 320GB GPU RAM

Hourly amount in source scope: USD $6.93/hr · Instance
Source billing unit: Instance-hour
176 CPU
960GB RAM
320GB GPU RAM

API record page

H200 NVL 141GB 2×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 30

Region not specified by provider

USD $7.24/hr

$3.62 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $7.24/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: H200 NVL (141GB) | 2 GPU | 1500 storage · Availability: Unknown · C · Display only

Reported GPU name: H200 NVL (141GB)

Reported VRAM: 141GB

Hourly amount in source scope: USD $7.24/hr · Instance
Source billing unit: Instance-hour
360 GB
141GB

API record page

GB300 SXM6 288GB 1×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $7.35/hr

$7.35 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $7.35/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 1GB300.32V · Availability: Unknown · A · Official API

Reported GPU name: 1x GB300 SXM6 288GB

Reported VRAM: 288GB GPU RAM

Hourly amount in source scope: USD $7.35/hr · Instance
Source billing unit: Instance-hour
32 CPU
225GB RAM
288GB GPU RAM

API record page

RTX PRO 4500 Blackwell 32GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 126

Region not specified by provider

USD $7.36/hr

$0.920 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $7.36/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: RTX PRO 4500 Blackwell (32GB) | 8 GPU | 6000 storage · Availability: Unknown · C · Display only

Reported GPU name: RTX PRO 4500 Blackwell (32GB)

Reported VRAM: 32GB

Hourly amount in source scope: USD $7.36/hr · Instance
Source billing unit: Instance-hour
592 GB
32GB

API record page

RTX PRO 6000 Blackwell MaxQ Works 96GB 4×

Clore.aiOn-demandTax unknownA · Official APICommunity marketplace

TW

USD (stablecoin) • platform fees may apply

USD $7.50/hr

$1.88 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $7.50/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 88789 · Availability: Available · A · Official API

Reported GPU name: NVIDIA RTX PRO 6000 Blackwell MaxQ Works

Reported VRAM: 96 GB

Hourly amount in source scope: USD $7.50/hr · Instance
Source billing unit: Instance-hour
64/128
512 GB
96 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

RTX PRO 6000 Blackwell MaxQ Works 96GB 4×

Clore.aiSpotTax unknownA · Official APICommunity marketplace

TW

USD (stablecoin) • platform fees may apply

USD $7.50/hr

$1.88 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $7.50/hr · Minimum billing duration unknown

View on Clore.ai →All offers →
Details & source

SKU: 88789 · Availability: Available · A · Official API

Reported GPU name: NVIDIA RTX PRO 6000 Blackwell MaxQ Works

Reported VRAM: 96 GB

Hourly amount in source scope: USD $7.50/hr · Instance
Source billing unit: Instance-hour
64/128
512 GB
96 GB

Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Stablecoin-denominated USD price (USD-Blockchain).

API record page

L40S 48GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 94

Region not specified by provider

USD $7.76/hr

$0.970 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $7.76/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: L40S (48GB) | 8 GPU | 5000 storage · Availability: Unknown · C · Display only

Reported GPU name: L40S (48GB)

Reported VRAM: 48GB

Hourly amount in source scope: USD $7.76/hr · Instance
Source billing unit: Instance-hour
576 GB
48GB

API record page

RTX PRO 6000 Blackwell Server Edition 96GB 2×

AWS EC2On-demandTax excludedA · Official API

vCPU: 48 · RAM (GiB): 512

us-east-1

USD $8.29/hr

$4.14 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $8.29/hr · Initial billing minimum: USD $0.138 / 60 seconds

View on AWS EC2 →All offers →
Details & source

SKU: g7e.12xlarge · Availability: Unknown · A · Official API

Reported GPU name: RTX PRO 6000 Blackwell Server Edition

Reported VRAM: 192 GB

Hourly amount in source scope: USD $8.29/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
192 GB

Linux, shared tenancy, no preinstalled software; storage and data transfer extra.

API record page

L40S 48GB 8×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $8.32/hr

$1.04 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $8.32/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 8L40S.160V · Availability: Unknown · A · Official API

Reported GPU name: 8x L40S 48GB

Reported VRAM: 384GB GPU RAM

Hourly amount in source scope: USD $8.32/hr · Instance
Source billing unit: Instance-hour
160 CPU
480GB RAM
384GB GPU RAM

API record page

RTX PRO 6000 Blackwell 96GB 4×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 60

Region not specified by provider

USD $8.76/hr

$2.19 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $8.76/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: RTX PRO 6000 Blackwell (96GB) [Reduced Storage] | 4 GPU | 1400 storage · Availability: Unknown · C · Display only

Reported GPU name: RTX PRO 6000 Blackwell (96GB) [Reduced Storage]

Reported VRAM: 96GB

Hourly amount in source scope: USD $8.76/hr · Instance
Source billing unit: Instance-hour
576 GB
96GB

API record page

MI300X 192GB 8×

AzureSpotTax unknownA · Official API

vCPU: 96 · RAM (GiB): 1850

eastus2

USD $8.87/hr

$1.11 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $8.87/hr · Minimum billing duration unknown

View on Azure →All offers →
Details & source

SKU: Standard_ND96isr_MI300X_v5 · Availability: Unknown · A · Official API

Reported GPU name: MI300X 192GB

Hourly amount in source scope: USD $8.87/hr · Instance
Source billing unit: Instance-hour

API record page

A100 SXM4 80GB 4×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $9.69/hr

$2.42 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $9.69/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4A100.88V · Availability: Unknown · A · Official API

Reported GPU name: 4x A100 SXM4 80GB

Reported VRAM: 320GB GPU RAM

Hourly amount in source scope: USD $9.69/hr · Instance
Source billing unit: Instance-hour
88 CPU
480GB RAM
320GB GPU RAM

API record page

A100 SXM4 80GB 8×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $9.69/hr

$1.21 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $9.69/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 8A100.176V · Availability: Unknown · A · Official API

Reported GPU name: 8x A100 SXM4 80GB

Reported VRAM: 640GB GPU RAM

Hourly amount in source scope: USD $9.69/hr · Instance
Source billing unit: Instance-hour
176 CPU
960GB RAM
640GB GPU RAM

API record page

B200 SXM6 180GB 1×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $9.80/hr

$9.80 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $9.80/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 1B200.30V · Availability: Unknown · A · Official API

Reported GPU name: 1x B200 SXM6 180GB

Reported VRAM: 180GB GPU RAM

Hourly amount in source scope: USD $9.80/hr · Instance
Source billing unit: Instance-hour
30 CPU
170GB RAM
180GB GPU RAM

API record page

H100 SXM 80GB 4×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $10.80/hr

$2.70 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $10.80/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4H100.80S.176V · Availability: Unknown · A · Official API

Reported GPU name: 4x H100 SXM5 80GB

Reported VRAM: 320GB GPU RAM

Hourly amount in source scope: USD $10.80/hr · Instance
Source billing unit: Instance-hour
176 CPU
680GB RAM
320GB GPU RAM

API record page

A100 80GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 120

Region not specified by provider

USD $10.80/hr

$1.35 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $10.80/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: A100 (80GB) | 8 GPU | 4096 storage · Availability: Unknown · C · Display only

Reported GPU name: A100 (80GB)

Reported VRAM: 80GB

Hourly amount in source scope: USD $10.80/hr · Instance
Source billing unit: Instance-hour
768 GB
80GB

API record page

H100 80GB 4×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 64

Region not specified by provider

USD $10.92/hr

$2.73 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $10.92/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: H100 (80GB) | 4 GPU | 5000 storage · Availability: Unknown · C · Display only

Reported GPU name: H100 (80GB)

Reported VRAM: 80GB

Hourly amount in source scope: USD $10.92/hr · Instance
Source billing unit: Instance-hour
512 GB
80GB

API record page

A100 SXM4 80GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 126

Region not specified by provider

USD $11.04/hr

$1.38 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $11.04/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: A100 SXM4 (80GB) | 8 GPU | 5000 storage · Availability: Unknown · C · Display only

Reported GPU name: A100 SXM4 (80GB)

Reported VRAM: 80GB

Hourly amount in source scope: USD $11.04/hr · Instance
Source billing unit: Instance-hour
800 GB
80GB

API record page

DGX A100 80GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 120

Region not specified by provider

USD $11.04/hr

$1.38 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $11.04/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: DGX A100 (80GB) | 8 GPU | 6000 storage · Availability: Unknown · C · Display only

Reported GPU name: DGX A100 (80GB)

Reported VRAM: 80GB

Hourly amount in source scope: USD $11.04/hr · Instance
Source billing unit: Instance-hour
1800 GB
80GB

API record page

H100 NVL 94GB 4×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 80

Region not specified by provider

USD $11.68/hr

$2.92 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $11.68/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: H100 NVL (94GB) NVLink | 4 GPU | 5000 storage · Availability: Unknown · C · Display only

Reported GPU name: H100 NVL (94GB) NVLink

Reported VRAM: 94GB

Hourly amount in source scope: USD $11.68/hr · Instance
Source billing unit: Instance-hour
512 GB
94GB

API record page

RTX PRO 6000 96GB 4×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $11.69/hr

$2.92 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $11.69/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4RTXPRO6000.120V · Availability: Unknown · A · Official API

Reported GPU name: 4x RTX PRO 6000 96GB

Reported VRAM: 384GB GPU RAM

Hourly amount in source scope: USD $11.69/hr · Instance
Source billing unit: Instance-hour
120 CPU
360GB RAM
384GB GPU RAM

API record page

RTX PRO 6000 96GB 8×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $11.69/hr

$1.46 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $11.69/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 8RTXPRO6000.240V · Availability: Unknown · A · Official API

Reported GPU name: 8x RTX PRO 6000 96GB

Reported VRAM: 768GB GPU RAM

Hourly amount in source scope: USD $11.69/hr · Instance
Source billing unit: Instance-hour
240 CPU
720GB RAM
768GB GPU RAM

API record page

H100 NVL 4×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 72

Region not specified by provider

USD $12.44/hr

$3.11 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $12.44/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: H100 NVL | 4 GPU | 3000 storage · Availability: Unknown · C · Display only

Reported GPU name: H100 NVL

Hourly amount in source scope: USD $12.44/hr · Instance
Source billing unit: Instance-hour
512 GB

API record page

H200 SXM5 141GB 2×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $13.81/hr

$6.91 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $13.81/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 2H200.141S.88V · Availability: Unknown · A · Official API

Reported GPU name: 2x H200 SXM5 141GB

Reported VRAM: 282GB GPU RAM

Hourly amount in source scope: USD $13.81/hr · Instance
Source billing unit: Instance-hour
88 CPU
340GB RAM
282GB GPU RAM

API record page

H200 SXM5 141GB 4×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $13.81/hr

$3.45 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $13.81/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4H200.141S.176V · Availability: Unknown · A · Official API

Reported GPU name: 4x H200 SXM5 141GB

Reported VRAM: 564GB GPU RAM

Hourly amount in source scope: USD $13.81/hr · Instance
Source billing unit: Instance-hour
176 CPU
680GB RAM
564GB GPU RAM

API record page

A100 SXM4 40GB 8×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $13.86/hr

$1.73 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $13.86/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 8A100.40S.176V · Availability: Unknown · A · Official API

Reported GPU name: 8x A100 SXM4 40GB

Reported VRAM: 320GB GPU RAM

Hourly amount in source scope: USD $13.86/hr · Instance
Source billing unit: Instance-hour
176 CPU
960GB RAM
320GB GPU RAM

API record page

H100 SXM 80GB 4×

ScalewayOn-demandTax excludedA · Official API

vCPU: 64 · RAM (GiB): 480

fr-par-2

USD $14.03/hr

$3.51 per GPU-hour

per instance-hour · checked

Original hourly price: EUR 12.771/hr · Instance

Minimum billable instance cost: USD $14.03/hr · Minimum billing duration unknown

View on Scaleway →All offers →
Details & source

SKU: /instance/server/h100_sxm_4_80g/fr-par-2 · Availability: Unknown · A · Official API

Reported GPU name: H100-SXM

Hourly amount in source scope: USD $14.03/hr · Instance
Source billing unit: Instance-minute
Original hourly price: EUR 12.771 · USD conversion rate: 1.0989 · ECB 2026-11-17
Intel Xeon Platinum 8452Y (2.0 GHz), x64, vCPUs: 64
480 GiB

API record page

H200 NVL 141GB 4×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 62

Region not specified by provider

USD $14.48/hr

$3.62 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $14.48/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: H200 NVL (141GB) | 4 GPU | 3000 storage · Availability: Unknown · C · Display only

Reported GPU name: H200 NVL (141GB)

Reported VRAM: 141GB

Hourly amount in source scope: USD $14.48/hr · Instance
Source billing unit: Instance-hour
720 GB
141GB

API record page

A10G 24GB 8×

AWS EC2On-demandTax excludedA · Official API

vCPU: 192 · RAM (GiB): 768

us-east-1

USD $16.29/hr

$2.04 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $16.29/hr · Initial billing minimum: USD $0.271 / 60 seconds

View on AWS EC2 →All offers →
Details & source

SKU: g5.48xlarge · Availability: Unknown · A · Official API

Reported GPU name: A10G

Reported VRAM: 192 GB

Hourly amount in source scope: USD $16.29/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
192 GB

Linux, shared tenancy, no preinstalled software; storage and data transfer extra.

API record page

RTX PRO 6000 Blackwell Server Edition 96GB 4×

AWS EC2On-demandTax excludedA · Official API

vCPU: 96 · RAM (GiB): 1024

us-east-1

USD $16.57/hr

$4.14 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $16.57/hr · Initial billing minimum: USD $0.276 / 60 seconds

View on AWS EC2 →All offers →
Details & source

SKU: g7e.24xlarge · Availability: Unknown · A · Official API

Reported GPU name: RTX PRO 6000 Blackwell Server Edition

Reported VRAM: 384 GB

Hourly amount in source scope: USD $16.57/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
384 GB

Linux, shared tenancy, no preinstalled software; storage and data transfer extra.

API record page

RTX PRO 6000 Blackwell 96GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 120

Region not specified by provider

USD $17.52/hr

$2.19 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $17.52/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: RTX PRO 6000 Blackwell (96GB) [Reduced Storage] | 8 GPU | 2800 storage · Availability: Unknown · C · Display only

Reported GPU name: RTX PRO 6000 Blackwell (96GB) [Reduced Storage]

Reported VRAM: 96GB

Hourly amount in source scope: USD $17.52/hr · Instance
Source billing unit: Instance-hour
1152 GB
96GB

API record page

A100 NVSwitch 80GB 4×

Baidu GPUOn-demandTax unknownC · Display only

Region not specified by provider

USD $18.11/hr

$4.53 per GPU-hour

per instance-hour · checked

Original hourly price: CNY 120.72/hr · Instance

Minimum billable instance cost: USD $18.11/hr · Minimum billing duration unknown

View on Baidu GPU →All offers →
Details & source

SKU: bcc.gn5.c56m480.4A100-80g · Availability: Unknown · C · Display only

Reported GPU name: 4*Nvidia A100 Nvswitch-80g

Reported VRAM: 320GB

Hourly amount in source scope: USD $18.11/hr · Instance
Source billing unit: Instance-hour
Original hourly price: CNY 120.72 · USD conversion rate: 0.150012 · ECB 2026-11-17
56核
480GB
320GB

API record page

H100 SXM 80GB 8×

AzureSpotTax unknownA · Official API

vCPU: 96 · RAM (GiB): 1900

eastus

USD $18.17/hr

$2.27 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $18.17/hr · Minimum billing duration unknown

View on Azure →All offers →
Details & source

SKU: Standard_ND96isr_H100_v5 · Availability: Unknown · A · Official API

Reported GPU name: H100 SXM 80GB

Hourly amount in source scope: USD $18.17/hr · Instance
Source billing unit: Instance-hour

API record page

B200 SXM6 180GB 2×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $19.59/hr

$9.79 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $19.59/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 2B200.60V · Availability: Unknown · A · Official API

Reported GPU name: 2x B200 SXM6 180GB

Reported VRAM: 360GB GPU RAM

Hourly amount in source scope: USD $19.59/hr · Instance
Source billing unit: Instance-hour
60 CPU
340GB RAM
360GB GPU RAM

API record page

B200 SXM6 180GB 4×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $19.59/hr

$4.90 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $19.59/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4B200.120V · Availability: Unknown · A · Official API

Reported GPU name: 4x B200 SXM6 180GB

Reported VRAM: 720GB GPU RAM

Hourly amount in source scope: USD $19.59/hr · Instance
Source billing unit: Instance-hour
120 CPU
680GB RAM
720GB GPU RAM

API record page

B200 CC SXM6 180GB 2×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $19.98/hr

$9.99 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $19.98/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 2B200.60V.CC.AMD · Availability: Unknown · A · Official API

Reported GPU name: 2x B200 CC SXM6 180GB

Reported VRAM: 360GB GPU RAM

Hourly amount in source scope: USD $19.98/hr · Instance
Source billing unit: Instance-hour
60 CPU (AMD EPYC)
340GB RAM
360GB GPU RAM

API record page

B200 CC SXM6 180GB 4×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $19.98/hr

$5.00 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $19.98/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4B200.120V.CC.AMD · Availability: Unknown · A · Official API

Reported GPU name: 4x B200 CC SXM6 180GB

Reported VRAM: 720GB GPU RAM

Hourly amount in source scope: USD $19.98/hr · Instance
Source billing unit: Instance-hour
120 CPU (AMD EPYC)
680GB RAM
720GB GPU RAM

API record page

A100 40GB 8×

AWS EC2On-demandTax excludedA · Official API

vCPU: 96 · RAM (GiB): 1152

us-east-1

USD $21.96/hr

$2.74 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $21.96/hr · Initial billing minimum: USD $0.366 / 60 seconds

View on AWS EC2 →All offers →
Details & source

SKU: p4d.24xlarge · Availability: Unknown · A · Official API

Reported GPU name: A100

Reported VRAM: 320 GB HBM2

Hourly amount in source scope: USD $21.96/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
320 GB HBM2

Linux, shared tenancy, no preinstalled software; storage and data transfer extra.

API record page

H100 NVL 94GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 140

Region not specified by provider

USD $23.36/hr

$2.92 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $23.36/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: H100 NVL (94GB) NVLink | 8 GPU | 10000 storage · Availability: Unknown · C · Display only

Reported GPU name: H100 NVL (94GB) NVLink

Reported VRAM: 94GB

Hourly amount in source scope: USD $23.36/hr · Instance
Source billing unit: Instance-hour
1500 GB
94GB

API record page

RTX PRO 6000 96GB 8×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $23.38/hr

$2.92 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $23.38/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 8RTXPRO6000.240V · Availability: Unknown · A · Official API

Reported GPU name: 8x RTX PRO 6000 96GB

Reported VRAM: 768GB GPU RAM

Hourly amount in source scope: USD $23.38/hr · Instance
Source billing unit: Instance-hour
240 CPU
720GB RAM
768GB GPU RAM

API record page

H100 NVL 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 140

Region not specified by provider

USD $24.88/hr

$3.11 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $24.88/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: H100 NVL | 8 GPU | 6000 storage · Availability: Unknown · C · Display only

Reported GPU name: H100 NVL

Hourly amount in source scope: USD $24.88/hr · Instance
Source billing unit: Instance-hour
1024 GB

API record page

H100 SXM 80GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 126

Region not specified by provider

USD $25.12/hr

$3.14 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $25.12/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: H100 SXM5 (80GB) | 8 GPU | 2800 storage · Availability: Unknown · C · Display only

Reported GPU name: H100 SXM5 (80GB)

Reported VRAM: 80GB

Hourly amount in source scope: USD $25.12/hr · Instance
Source billing unit: Instance-hour
976 GB
80GB

API record page

B300 CC SXM6 268GB 4×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $26.09/hr

$6.52 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $26.09/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4B300.120V.CC.AMD · Availability: Unknown · A · Official API

Reported GPU name: 4x B300 CC SXM6 268GB

Reported VRAM: 1072GB GPU RAM

Hourly amount in source scope: USD $26.09/hr · Instance
Source billing unit: Instance-hour
120 CPU (AMD EPYC)
1020GB RAM
1072GB GPU RAM

API record page

H200 SXM5 141GB 4×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $27.62/hr

$6.91 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $27.62/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4H200.141S.176V · Availability: Unknown · A · Official API

Reported GPU name: 4x H200 SXM5 141GB

Reported VRAM: 564GB GPU RAM

Hourly amount in source scope: USD $27.62/hr · Instance
Source billing unit: Instance-hour
176 CPU
680GB RAM
564GB GPU RAM

API record page

H200 SXM5 141GB 8×

Verda / DataCrunchSpotTax unknownA · Official API

Region not specified by provider

USD $27.62/hr

$3.45 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $27.62/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 8H200.141S.176V · Availability: Unknown · A · Official API

Reported GPU name: 8x H200 SXM5 141GB

Reported VRAM: 1128GB GPU RAM

Hourly amount in source scope: USD $27.62/hr · Instance
Source billing unit: Instance-hour
176 CPU
1360GB RAM
1128GB GPU RAM

API record page

RTX PRO 4500 32GB 8×

AWS EC2On-demandTax excludedA · Official API

vCPU: 192 · RAM (GiB): 768

us-east-1

USD $28.51/hr

$3.56 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $28.51/hr · Initial billing minimum: USD $0.475 / 60 seconds

View on AWS EC2 →All offers →
Details & source

SKU: g7.48xlarge · Availability: Unknown · A · Official API

Reported GPU name: RTX PRO 4500

Reported VRAM: 256 GB

Hourly amount in source scope: USD $28.51/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
256 GB

Linux, shared tenancy, no preinstalled software; storage and data transfer extra.

API record page

H200 NVL 141GB 8×

Massed ComputeOn-demandTax unknownC · Display only

vCPU: 120

Region not specified by provider

USD $28.96/hr

$3.62 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $28.96/hr · Minimum billing duration unknown

View on Massed Compute →All offers →
Details & source

SKU: H200 NVL (141GB) | 8 GPU | 6000 storage · Availability: Unknown · C · Display only

Reported GPU name: H200 NVL (141GB)

Reported VRAM: 141GB

Hourly amount in source scope: USD $28.96/hr · Instance
Source billing unit: Instance-hour
1760 GB
141GB

API record page

A100 NVSwitch 40GB 8×

Baidu GPUOn-demandTax unknownC · Display only

Region not specified by provider

USD $31.30/hr

$3.91 per GPU-hour

per instance-hour · checked

Original hourly price: CNY 208.67/hr · Instance

Minimum billable instance cost: USD $31.30/hr · Minimum billing duration unknown

View on Baidu GPU →All offers →
Details & source

SKU: bcc.gn5.c112m896.8A100-40g · Availability: Unknown · C · Display only

Reported GPU name: 8*Nvidia A100 Nvswitch-40g

Reported VRAM: 320GB

Hourly amount in source scope: USD $31.30/hr · Instance
Source billing unit: Instance-hour
Original hourly price: CNY 208.67 · USD conversion rate: 0.150012 · ECB 2026-11-17
112核
896GB
320GB

API record page

RTX PRO 6000 Blackwell Server Edition 96GB 8×

AWS EC2On-demandTax excludedA · Official API

vCPU: 192 · RAM (GiB): 2048

us-east-1

USD $33.14/hr

$4.14 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $33.14/hr · Initial billing minimum: USD $0.552 / 60 seconds

View on AWS EC2 →All offers →
Details & source

SKU: g7e.48xlarge · Availability: Unknown · A · Official API

Reported GPU name: RTX PRO 6000 Blackwell Server Edition

Reported VRAM: 768 GB

Hourly amount in source scope: USD $33.14/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
768 GB

Linux, shared tenancy, no preinstalled software; storage and data transfer extra.

API record page

A100 NVSwitch 80GB 8×

Baidu GPUOn-demandTax unknownC · Display only

Region not specified by provider

USD $36.22/hr

$4.53 per GPU-hour

per instance-hour · checked

Original hourly price: CNY 241.43/hr · Instance

Minimum billable instance cost: USD $36.22/hr · Minimum billing duration unknown

View on Baidu GPU →All offers →
Details & source

SKU: bcc.gn5.c112m960.8A100-80g · Availability: Unknown · C · Display only

Reported GPU name: 8*Nvidia A100 Nvswitch-80g

Reported VRAM: 640GB

Hourly amount in source scope: USD $36.22/hr · Instance
Source billing unit: Instance-hour
Original hourly price: CNY 241.43 · USD conversion rate: 0.150012 · ECB 2026-11-17
112核
960GB
640GB

API record page

H200 141GB 8×

OVHcloudOn-demandTax excludedA · Official API

vCPU: 224

Region not specified by provider

USD $46.15/hr

$5.77 per GPU-hour

per instance-hour · checked

Original hourly price: EUR 42/hr · Instance

Minimum billable instance cost: USD $46.15/hr · Initial billing minimum: USD $0.769 / 60 seconds

View on OVHcloud →All offers →
Details & source

SKU: h200-1920-eph.consumption · Availability: Unknown · A · Official API

Reported GPU name: H200

Reported VRAM: 141 GB/GPU

Hourly amount in source scope: USD $46.15/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
Original hourly price: EUR 42 · USD conversion rate: 1.0989 · ECB 2026-11-17
1920 GB
141 GB/GPU

FR subsidiary base Linux public-cloud catalog; exact region and capacity unspecified; local/3-AZ prices not inferred.

API record page

MI300X 192GB 8×

AzureOn-demandTax unknownA · Official API

vCPU: 96 · RAM (GiB): 1850

eastus2

USD $48.00/hr

$6.00 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $48.00/hr · Minimum billing duration unknown

View on Azure →All offers →
Details & source

SKU: Standard_ND96isr_MI300X_v5 · Availability: Unknown · A · Official API

Reported GPU name: MI300X 192GB

Hourly amount in source scope: USD $48.00/hr · Instance
Source billing unit: Instance-hour

API record page

B300 CC SXM6 268GB 4×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $52.18/hr

$13.04 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $52.18/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4B300.120V.CC.AMD · Availability: Unknown · A · Official API

Reported GPU name: 4x B300 CC SXM6 268GB

Reported VRAM: 1072GB GPU RAM

Hourly amount in source scope: USD $52.18/hr · Instance
Source billing unit: Instance-hour
120 CPU (AMD EPYC)
1020GB RAM
1072GB GPU RAM

API record page

H100 80GB 8×

AWS EC2On-demandTax excludedA · Official API

vCPU: 192 · RAM (GiB): 2048

us-east-1

USD $55.04/hr

$6.88 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $55.04/hr · Initial billing minimum: USD $0.917 / 60 seconds

View on AWS EC2 →All offers →
Details & source

SKU: p5.48xlarge · Availability: Unknown · A · Official API

Reported GPU name: H100

Reported VRAM: 640 GB HBM3

Hourly amount in source scope: USD $55.04/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
640 GB HBM3

Linux, shared tenancy, no preinstalled software; storage and data transfer extra.

API record page

H200 SXM5 141GB 8×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $55.23/hr

$6.90 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $55.23/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 8H200.141S.176V · Availability: Unknown · A · Official API

Reported GPU name: 8x H200 SXM5 141GB

Reported VRAM: 1128GB GPU RAM

Hourly amount in source scope: USD $55.23/hr · Instance
Source billing unit: Instance-hour
176 CPU
1360GB RAM
1128GB GPU RAM

API record page

GB300 SXM6 288GB 4×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $58.83/hr

$14.71 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $58.83/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 4GB300.128V · Availability: Unknown · A · Official API

Reported GPU name: 4x GB300 SXM6 288GB

Reported VRAM: 1152GB GPU RAM

Hourly amount in source scope: USD $58.83/hr · Instance
Source billing unit: Instance-hour
128 CPU
900GB RAM
1152GB GPU RAM

API record page

H200 141GB 8×

AzureSpotTax unknownA · Official API

vCPU: 96 · RAM (GiB): 1850

eastus2

USD $84.80/hr

$10.60 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $84.80/hr · Minimum billing duration unknown

View on Azure →All offers →
Details & source

SKU: Standard_ND96isr_H200_v5 · Availability: Unknown · A · Official API

Reported GPU name: H200 141GB

Hourly amount in source scope: USD $84.80/hr · Instance
Source billing unit: Instance-hour

API record page

B300 SXM6 268GB 8×

Verda / DataCrunchOn-demandTax unknownA · Official API

Region not specified by provider

USD $102.30/hr

$12.79 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $102.30/hr · Minimum billing duration unknown

View on Verda / DataCrunch →All offers →
Details & source

SKU: 8B300.240V · Availability: Unknown · A · Official API

Reported GPU name: 8x B300 SXM6 268GB

Reported VRAM: 2144GB GPU RAM

Hourly amount in source scope: USD $102.30/hr · Instance
Source billing unit: Instance-hour
240 CPU
2040GB RAM
2144GB GPU RAM

API record page

B200 180GB 8×

Oracle CloudOn-demandTax unknownA · Official API

Region not specified by provider

USD $112.00/hr

$14.00 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $112.00/hr · Minimum billing duration unknown

View on Oracle Cloud →All offers →
Details & source

SKU: B110978:BM.GPU.B200.8 · Availability: Unknown · A · Official API

Reported GPU name: OCI - Compute - GPU - B200

Hourly amount in source scope: USD $112.00/hr · Instance
Source billing unit: Instance-hour
128 OCPUs
4096 GB

Global public list rate; region and inventory unspecified. Shape CPU and memory included.

API record page

B200 179GB 8×

AWS EC2On-demandTax excludedA · Official API

vCPU: 192 · RAM (GiB): 2048

us-east-1

USD $113.93/hr

$14.24 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $113.93/hr · Initial billing minimum: USD $1.90 / 60 seconds

View on AWS EC2 →All offers →
Details & source

SKU: p6-b200.48xlarge · Availability: Unknown · A · Official API

Reported GPU name: B200

Reported VRAM: 1432 GB HBM3e

Hourly amount in source scope: USD $113.93/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
1432 GB HBM3e

Linux, shared tenancy, no preinstalled software; storage and data transfer extra.

API record page

B300 268GB 8×

AWS EC2On-demandTax excludedA · Official API

vCPU: 192 · RAM (GiB): 4096

us-east-1

USD $142.42/hr

$17.80 per GPU-hour

per instance-hour · checked

Minimum billable instance cost: USD $142.42/hr · Initial billing minimum: USD $2.37 / 60 seconds

View on AWS EC2 →All offers →
Details & source

SKU: p6-b300.48xlarge · Availability: Unknown · A · Official API

Reported GPU name: B300

Reported VRAM: 2144 GB HBM3e

Hourly amount in source scope: USD $142.42/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
2144 GB HBM3e

Linux, shared tenancy, no preinstalled software; storage and data transfer extra.

API record page

What to check before renting

Official sources

Know the full job cost before you rent: GPU Budget Kit ($12)

Rental guides and weekly price reports