Best cloud GPU for Qwen2.5 7B Instruct LLM inference (FP16)
Compare whole-GPU quotes for Qwen2.5 7B Instruct. “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: 7.615616512B parameters × 2 bytes/parameter = 15.2312 GB weights; required = 15.2312 × 1.2 + 0.47 GB FP16 KV cache at 8192 tokens = 18.747 GB.
Exact input: 7615616512 parameters, derived from the official configuration (hidden size 3584, intermediate size 18944, vocabulary 152064, including embeddings, output projection, norms and any Q/K/V biases), cross-checked against the BF16 weight index total_size / 2. We use 8192 tokens, below the configured maximum of 32768; no context extension is assumed.
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 × 28 layers × 4 KV heads × head dimension 128 × 2 bytes × 8192 tokens / 10⁹ = 0.47 GB, batch 1.
Tensor-parallel inputs: 28 attention heads and 4 KV heads; GPU count must divide both.
The same memory estimate applies to DeepSeek-R1-Distill-Qwen-7B: the official configs have the same weight and KV dimensions at this context and precision; this does not establish identical behavior or runtime usage.
Model-developer cross-check, Qwen: Qwen: speed and GPU-memory benchmark. Transformers 4.46.0, PyTorch 2.3.1, CUDA 12.1, A100 80GB; batch 1, input 6144 + output 2048 tokens. The benchmark labels memory GB, but Qwen: benchmark memory calculation (bytes / 1024³) sums peak allocated bytes across GPUs and divides by 1024³: these are GiB. We convert to decimal GB for screening (1 GiB = 1.073741824 GB). The benchmark does not list vLLM memory because vLLM preallocates GPU memory.
BF16 measurement published by Qwen: 15.38 GiB total across 1 GPU(s). BF16 and FP16 both store weights in two bytes, but use different formats and can have different runtime usage.
Governing capacity screen: max(our estimate 18.747 GB, model-developer peak 16.514 GB after conversion) = 18.747 GB. A single GPU, or the total capacity of an eligible tensor-parallel instance, must meet this figure. For 4-bit we use the larger GPTQ/AWQ peak.
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: 1810. Distinct model/type minima shown: 126.
“Best” on this page
On-demand: RTX 4000 Ada 20GB · Clore.ai · 1 GPU per instance · $0.092 per instance-hour
Spot: RTX 3090 24GB · Clore.ai · 1 GPU per instance · $0.067 per instance-hour
One GPU’s memory is enough: cheapest instance
On-demand: RTX 4000 Ada 20GB · Clore.ai · 1 GPU per instance · $0.092 per instance-hour
Spot: RTX 3090 24GB · Clore.ai · 1 GPU per instance · $0.067 per instance-hour
Cheapest multi-GPU instance
On-demand: RTX 3060 12GB · Clore.ai · 2 GPUs per instance · $0.083 per instance-hour
Spot: RTX 3060 12GB · Clore.ai · 2 GPUs per instance · $0.065 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
| GPU model | Reviewed GB per GPU | Price type | Per GPU $/hr | GPUs per instance | Instance $/hr | Estimated headroom (single: per GPU; multi: total) | Reviewed architecture and checks |
|---|---|---|---|---|---|---|---|
| RTX 3090 24GB | 24 | Spot | $0.067 | 1 | $0.067 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 |
| L4 24GB | 23 | Spot | $0.083 | 4 | $0.333 | tight < 1.25× (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs |
| RTX 3090 24GB | 24 | On-demand | $0.088 | 2 | $0.175 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · one GPU’s memory passes, but this offer is sold only as an instance with 2 GPUs |
| RTX 4000 Ada 20GB | 19 | On-demand | $0.092 | 1 | $0.092 | tight < 1.25× (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 |
| RTX 4000 Ada 20GB | 19 | Spot | $0.092 | 1 | $0.092 | tight < 1.25× (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 |
| L4 24GB | 23 | On-demand | $0.104 | 4 | $0.417 | tight < 1.25× (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs |
| Quadro RTX 6000 24GB | 24 | Spot | $0.125 | 1 | $0.125 | comfortable (estimate) | NVIDIA · Turing · CUDA CC 7.5 |
| RTX A5000 24GB | 24 | On-demand | $0.142 | 8 | $1.13 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs |
| RTX A5000 24GB | 24 | Spot | $0.142 | 8 | $1.13 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs |
| Quadro RTX 6000 24GB | 24 | On-demand | $0.154 | 1 | $0.154 | comfortable (estimate) | NVIDIA · Turing · CUDA CC 7.5 |
| RTX PRO 4000 Blackwell 24GB | 24 | Spot | $0.188 | 4 | $0.750 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs |
| RTX 4090 24GB | 24 | Spot | $0.208 | 1 | $0.208 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 |
| RTX PRO 4000 Blackwell 24GB | 24 | On-demand | $0.208 | 4 | $0.833 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs |
| RTX 4090 24GB | 24 | On-demand | $0.212 | 1 | $0.212 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 |
| A100 PCIe 80GB | 80 | Spot | $0.250 | 1 | $0.250 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 |
| RTX 5090 32GB | 32 | Spot | $0.250 | 1 | $0.250 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| RTX 5090 D v2 24GB | 24 | Spot | $0.338 | 1 | $0.338 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| RTX 5090 32GB | 32 | On-demand | $0.344 | 4 | $1.38 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs |
| A30 24GB | 24 | On-demand | $0.350 | 1 | $0.350 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 |
| A100 PCIe 80GB | 80 | On-demand | $0.354 | 1 | $0.354 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 |
| RTX 3090 20GB | 20 | On-demand | $0.375 | 1 | $0.375 | tight < 1.25× (estimate) | NVIDIA · Ampere · CUDA CC 8.6 |
| RTX 3090 20GB | 20 | Spot | $0.375 | 1 | $0.375 | tight < 1.25× (estimate) | NVIDIA · Ampere · CUDA CC 8.6 |
| RTX 5090 D v2 24GB | 24 | On-demand | $0.377 | 1 | $0.377 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| RTX 3090 Ti 24GB | 24 | On-demand | $0.417 | 3 | $1.25 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · one GPU’s memory passes, but this offer is sold only as an instance with 3 GPUs |
| RTX 3090 Ti 24GB | 24 | Spot | $0.417 | 3 | $1.25 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · one GPU’s memory passes, but this offer is sold only as an instance with 3 GPUs |
| RTX A6000 48GB | 48 | Spot | $0.458 | 1 | $0.458 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 |
| H100 NVL 94GB | 94 | Spot | $0.458 | 2 | $0.917 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 · one GPU’s memory passes, but this offer is sold only as an instance with 2 GPUs |
| RTX A6000 48GB | 48 | On-demand | $0.550 | 1 | $0.550 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 |
| A100 SXM4 40GB | 40 | Spot | $0.583 | 2 | $1.17 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 · one GPU’s memory passes, but this offer is sold only as an instance with 2 GPUs |
| A10 24GB | 24 | Spot | $0.591 | 1 | $0.591 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 |
| A100 40GB | 40 | Spot | $0.738 | 8 | $5.90 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs |
| RTX 6000 Ada 48GB | 48 | On-demand | $0.790 | 1 | $0.790 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 |
| A100 SXM4 40GB | 40 | On-demand | $0.792 | 2 | $1.58 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 · one GPU’s memory passes, but this offer is sold only as an instance with 2 GPUs |
| RTX 6000 Ada 48GB | 48 | Spot | $0.827 | 1 | $0.827 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 |
| H100 NVL 94GB | 94 | On-demand | $0.833 | 2 | $1.67 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 · one GPU’s memory passes, but this offer is sold only as an instance with 2 GPUs |
| A10 24GB | 24 | On-demand | $0.835 | 1 | $0.835 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 |
| A100 80GB | 80 | Spot | $0.859 | 8 | $6.87 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs |
| L40 48GB | 48 | On-demand | $0.860 | 1 | $0.860 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 |
| RTX PRO 6000 Blackwell Workstation 96GB | 96 | On-demand | $0.875 | 1 | $0.875 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| RTX PRO 6000 Blackwell Workstation 96GB | 96 | Spot | $0.875 | 1 | $0.875 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| RTX PRO 4500 Blackwell 32GB | 32 | On-demand | $0.920 | 1 | $0.920 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| L40S 48GB | 48 | On-demand | $0.970 | 1 | $0.970 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 |
| A10G 24GB | 24 | On-demand | $1.01 | 1 | $1.01 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 |
| L40S 48GB | 48 | Spot | $1.04 | 2 | $2.08 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · one GPU’s memory passes, but this offer is sold only as an instance with 2 GPUs |
| MI300X 192GB | 192 | Spot | $1.11 | 8 | $8.87 | comfortable (estimate) | AMD · CDNA 3 · gfx942 · non-CUDA · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs |
| A100 SXM4 80GB | 80 | Spot | $1.21 | 1 | $1.21 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 |
| A100 80GB | 80 | On-demand | $1.35 | 1 | $1.35 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 |
| A10 PCIe 24GB | 24 | On-demand | $1.37 | 1 | $1.37 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 |
| A100 SXM4 80GB | 80 | On-demand | $1.38 | 1 | $1.38 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 |
| DGX A100 80GB | 80 | On-demand | $1.38 | 1 | $1.38 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 |
| RTX PRO 6000 96GB | 96 | Spot | $1.46 | 1 | $1.46 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| RTX PRO 6000 CC 96GB | 96 | Spot | $1.49 | 1 | $1.49 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| H200 141GB | 141 | On-demand | $1.75 | 1 | $1.75 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 |
| H200 141GB | 141 | Spot | $1.75 | 1 | $1.75 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 |
| RTX PRO 6000 Blackwell MaxQ Works 96GB | 96 | On-demand | $1.88 | 4 | $7.50 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs |
| RTX PRO 6000 Blackwell MaxQ Works 96GB | 96 | Spot | $1.88 | 4 | $7.50 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs |
| RTX PRO 6000 Blackwell 96GB | 96 | On-demand | $2.19 | 1 | $2.19 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| H100 SXM 80GB | 80 | Spot | $2.27 | 8 | $18.17 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs |
| RTX PRO 4500 32GB | 32 | On-demand | $2.52 | 1 | $2.52 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| H100 80GB | 80 | On-demand | $2.73 | 1 | $2.73 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 |
| A100 40GB | 40 | On-demand | $2.74 | 8 | $21.96 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs |
| RTX PRO 6000 96GB | 96 | On-demand | $2.92 | 1 | $2.92 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| RTX PRO 6000 CC 96GB | 96 | On-demand | $2.98 | 1 | $2.98 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| H100 NVL | 94 | On-demand | $3.11 | 1 | $3.11 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 |
| H100 SXM 80GB | 80 | On-demand | $3.14 | 1 | $3.14 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 |
| H100 PCIe 80GB | 80 | On-demand | $3.15 | 1 | $3.15 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 |
| RTX PRO 6000 Blackwell Server Edition 96GB | 96 | On-demand | $3.36 | 1 | $3.36 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 |
| H200 SXM5 141GB | 141 | Spot | $3.45 | 1 | $3.45 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 |
| H200 NVL 141GB | 141 | On-demand | $3.62 | 1 | $3.62 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 |
| A100 NVSwitch 40GB | 40 | On-demand | $3.91 | 8 | $31.30 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs |
| A100 NVSwitch 80GB | 80 | On-demand | $4.53 | 8 | $36.22 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.0 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs |
| B200 SXM6 180GB | 180 | Spot | $4.90 | 4 | $19.59 | comfortable (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 180GB | 180 | Spot | $5.00 | 4 | $19.98 | comfortable (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 192GB | 192 | On-demand | $6.00 | 8 | $48.00 | comfortable (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 268GB | 268 | Spot | $6.39 | 1 | $6.39 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 10.3 |
| B300 CC SXM6 268GB | 268 | Spot | $6.52 | 4 | $26.09 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 10.3 · one GPU’s memory passes, but this offer is sold only as an instance with 4 GPUs |
| H200 SXM5 141GB | 141 | On-demand | $6.90 | 8 | $55.23 | comfortable (estimate) | NVIDIA · Hopper · CUDA CC 9.0 · one GPU’s memory passes, but this offer is sold only as an instance with 8 GPUs |
| B200 SXM6 180GB | 180 | On-demand | $9.79 | 2 | $19.59 | comfortable (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 180GB | 180 | On-demand | $9.99 | 2 | $19.98 | comfortable (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 268GB | 268 | On-demand | $12.79 | 8 | $102.30 | comfortable (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 268GB | 268 | On-demand | $13.04 | 4 | $52.18 | comfortable (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 180GB | 180 | On-demand | $14.00 | 8 | $112.00 | comfortable (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 179GB | 179 | On-demand | $14.24 | 8 | $113.93 | comfortable (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 268GB | 268 | On-demand | $17.80 | 8 | $142.42 | comfortable (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.
| GPU model | Reviewed GB per GPU | Price type | Per GPU $/hr | GPUs per instance | Instance $/hr | Estimated headroom (single: per GPU; multi: total) | Reviewed architecture and checks |
|---|---|---|---|---|---|---|---|
| RTX 3060 12GB | 12 | Spot | $0.032 | 2 | $0.065 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3060 12GB | 12 | On-demand | $0.042 | 2 | $0.083 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX A4000 16GB | 16 | Spot | $0.079 | 2 | $0.158 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3080 10GB | 10 | On-demand | $0.088 | 2 | $0.175 | tight < 1.25× (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3080 10GB | 10 | Spot | $0.088 | 2 | $0.175 | tight < 1.25× (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4070 12GB | 12 | Spot | $0.092 | 2 | $0.185 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4070 12GB | 12 | On-demand | $0.092 | 2 | $0.185 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX A4000 16GB | 16 | On-demand | $0.094 | 2 | $0.188 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX PRO 2000 Blackwell 16GB | 16 | On-demand | $0.094 | 2 | $0.188 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX PRO 2000 Blackwell 16GB | 16 | Spot | $0.094 | 2 | $0.188 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3060 12GB | 12 | On-demand | $0.052 | 4 | $0.208 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3060 12GB | 12 | Spot | $0.052 | 4 | $0.208 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5070 12GB | 12 | Spot | $0.113 | 2 | $0.225 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5070 12GB | 12 | On-demand | $0.113 | 2 | $0.225 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5060 Ti 16GB | 16 | On-demand | $0.115 | 2 | $0.229 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5060 Ti 16GB | 16 | Spot | $0.115 | 2 | $0.229 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3060 Ti 8GB | 8 | Spot | $0.062 | 4 | $0.250 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3060 Ti 8GB | 8 | On-demand | $0.062 | 4 | $0.250 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4080 SUPER 16GB | 16 | On-demand | $0.133 | 2 | $0.267 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4070 Ti SUPER 16GB | 16 | Spot | $0.133 | 2 | $0.267 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3070 8GB | 8 | On-demand | $0.068 | 4 | $0.271 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3070 8GB | 8 | Spot | $0.068 | 4 | $0.271 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5070 Ti 16GB | 16 | Spot | $0.155 | 2 | $0.310 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4070 Ti SUPER 16GB | 16 | On-demand | $0.156 | 2 | $0.312 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5080 16GB | 16 | Spot | $0.157 | 2 | $0.315 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3080 Ti 12GB | 12 | On-demand | $0.167 | 2 | $0.333 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 2080 Ti 11GB | 11 | On-demand | $0.167 | 2 | $0.333 | tight < 1.25× (estimate) | NVIDIA · Turing · CUDA CC 7.5 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 2080 Ti 11GB | 11 | Spot | $0.167 | 2 | $0.333 | tight < 1.25× (estimate) | NVIDIA · Turing · CUDA CC 7.5 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3080 12GB | 12 | Spot | $0.167 | 2 | $0.333 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3080 Ti 12GB | 12 | Spot | $0.167 | 2 | $0.333 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3080 10GB | 10 | Spot | $0.083 | 4 | $0.333 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5080 16GB | 16 | On-demand | $0.187 | 2 | $0.375 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3080 10GB | 10 | On-demand | $0.094 | 4 | $0.375 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3080 12GB | 12 | On-demand | $0.188 | 2 | $0.375 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4070 SUPER 12GB | 12 | On-demand | $0.188 | 2 | $0.375 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4070 SUPER 12GB | 12 | Spot | $0.188 | 2 | $0.375 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5070 Ti 16GB | 16 | On-demand | $0.188 | 2 | $0.375 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4070 Ti 12GB | 12 | Spot | $0.202 | 2 | $0.403 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4070 Ti 12GB | 12 | On-demand | $0.206 | 2 | $0.412 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5060 Ti 7GB | 7 | On-demand | $0.104 | 4 | $0.417 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5060 Ti 7GB | 7 | Spot | $0.104 | 4 | $0.417 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5070 12GB | 12 | Spot | $0.114 | 4 | $0.456 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4080 16GB | 16 | On-demand | $0.263 | 2 | $0.525 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4080 16GB | 16 | Spot | $0.263 | 2 | $0.525 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5070 Ti 16GB | 16 | Spot | $0.135 | 4 | $0.539 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5070 12GB | 12 | On-demand | $0.136 | 4 | $0.542 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4070 Ti 12GB | 12 | On-demand | $0.156 | 4 | $0.625 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4070 Ti 12GB | 12 | Spot | $0.156 | 4 | $0.625 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 4080 SUPER 16GB | 16 | Spot | $0.333 | 2 | $0.667 | comfortable (estimate) | NVIDIA · Ada Lovelace · CUDA CC 8.9 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5070 Ti 16GB | 16 | On-demand | $0.173 | 4 | $0.691 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3080 Ti 12GB | 12 | On-demand | $0.208 | 4 | $0.833 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 3080 Ti 12GB | 12 | Spot | $0.208 | 4 | $0.833 | comfortable (estimate) | NVIDIA · Ampere · CUDA CC 8.6 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5080 16GB | 16 | On-demand | $0.229 | 4 | $0.917 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| RTX 5080 16GB | 16 | Spot | $0.229 | 4 | $0.917 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 12.0 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect |
| T4 16GB | 16 | Spot | $0.309 | 4 | $1.23 | comfortable (estimate) | NVIDIA · Turing · CUDA CC 7.5 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect · PCIe only, no NVLink; vLLM suggests pipeline parallelism |
| T4 16GB | 16 | On-demand | $1.25 | 2 | $2.49 | comfortable (estimate) | NVIDIA · Turing · CUDA CC 7.5 · tensor parallel across 2 GPUs; needs a serving engine with TP support; check the interconnect · PCIe only, no NVLink; vLLM suggests pipeline parallelism |
| T4 16GB | 16 | On-demand | $0.978 | 4 | $3.91 | comfortable (estimate) | NVIDIA · Turing · CUDA CC 7.5 · tensor parallel across 4 GPUs; needs a serving engine with TP support; check the interconnect · PCIe only, no NVLink; vLLM suggests pipeline parallelism |
Meets memory only, check software support
| GPU model | Reviewed GB per GPU | Price type | Per GPU $/hr | GPUs per instance | Instance $/hr | Estimated headroom (single: per GPU; multi: total) | Reviewed architecture and checks |
|---|---|---|---|---|---|---|---|
| V100 SXM2 32GB | 32 | On-demand | $0.074 | 4 | $0.295 | comfortable (estimate) | NVIDIA · Volta · CUDA CC 7.0 · below floor |
| V100 SXM2 32GB | 32 | Spot | $0.074 | 4 | $0.295 | comfortable (estimate) | NVIDIA · Volta · CUDA CC 7.0 · below floor |
| Tesla M40 24GB | 23 | On-demand | $0.074 | 1 | $0.074 | tight < 1.25× (estimate) | NVIDIA · Maxwell · CUDA CC 5.2 · below floor |
| Tesla M40 24GB | 23 | Spot | $0.074 | 1 | $0.074 | tight < 1.25× (estimate) | NVIDIA · Maxwell · CUDA CC 5.2 · below floor |
| P40 24GB | 23 | On-demand | $0.101 | 1 | $0.101 | tight < 1.25× (estimate) | NVIDIA · Pascal · CUDA CC 6.1 · below floor |
| P40 24GB | 23 | Spot | $0.101 | 1 | $0.101 | tight < 1.25× (estimate) | NVIDIA · Pascal · CUDA CC 6.1 · below floor |
| V100 32GB | 32 | Spot | $0.509 | 8 | $4.07 | comfortable (estimate) | NVIDIA · Volta · CUDA CC 7.0 · below floor |
| V100 32GB | 32 | On-demand | $2.33 | 2 | $4.65 | comfortable (estimate) | NVIDIA · Volta · CUDA CC 7.0 · below floor |
| GB300 SXM6 288GB | 288 | Spot | $7.35 | 1 | $7.35 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 10.3 · Arm (aarch64) host · below floor |
| GB300 SXM6 288GB | 288 | On-demand | $14.71 | 4 | $58.83 | comfortable (estimate) | NVIDIA · Blackwell · CUDA CC 10.3 · Arm (aarch64) host · below floor |
RTX 3060 12GB 2×
MX
USD (stablecoin) • platform fees may apply
$0.032 per GPU-hour
Minimum billable instance cost: USD $0.065/hr · Minimum billing duration unknown
Details & source
SKU: 123848 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3060
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.065/hr · Instance
Source billing unit: Instance-hour
6/12
8 GB
12 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 pageRTX 3090 24GB 1×
PL
USD (stablecoin) • platform fees may apply
$0.067 per GPU-hour
Minimum billable instance cost: USD $0.067/hr · Minimum billing duration unknown
Details & source
SKU: 112743 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3090
Reported VRAM: 24 GB
Hourly amount in source scope: USD $0.067/hr · Instance
Source billing unit: Instance-hour
16/32
64 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 pageTesla M40 24GB 1×
MO
USD (stablecoin) • platform fees may apply
$0.074 per GPU-hour
Minimum billable instance cost: USD $0.074/hr · Minimum billing duration unknown
Details & source
SKU: 123106 · Availability: Available · A · Official API
Reported GPU name: Tesla M40 24GB
Reported VRAM: 23 GB
Hourly amount in source scope: USD $0.074/hr · Instance
Source billing unit: Instance-hour
12/24
32 GB
23 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 pageTesla M40 24GB 1×
MO
USD (stablecoin) • platform fees may apply
$0.074 per GPU-hour
Minimum billable instance cost: USD $0.074/hr · Minimum billing duration unknown
Details & source
SKU: 123106 · Availability: Available · A · Official API
Reported GPU name: Tesla M40 24GB
Reported VRAM: 23 GB
Hourly amount in source scope: USD $0.074/hr · Instance
Source billing unit: Instance-hour
12/24
32 GB
23 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 pageRTX 3060 12GB 2×
MX
USD (stablecoin) • platform fees may apply
$0.042 per GPU-hour
Minimum billable instance cost: USD $0.083/hr · Minimum billing duration unknown
Details & source
SKU: 123922 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3060
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.083/hr · Instance
Source billing unit: Instance-hour
6/12
8 GB
12 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 pageRTX 4000 Ada 20GB 1×
BR
USD (stablecoin) • platform fees may apply
$0.092 per GPU-hour
Minimum billable instance cost: USD $0.092/hr · Minimum billing duration unknown
Details & source
SKU: 119352 · Availability: Available · A · Official API
Reported GPU name: NVIDIA RTX 4000 Ada Generation
Reported VRAM: 19 GB
Hourly amount in source scope: USD $0.092/hr · Instance
Source billing unit: Instance-hour
12/24
128 GB
19 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 pageRTX 4000 Ada 20GB 1×
BR
USD (stablecoin) • platform fees may apply
$0.092 per GPU-hour
Minimum billable instance cost: USD $0.092/hr · Minimum billing duration unknown
Details & source
SKU: 119352 · Availability: Available · A · Official API
Reported GPU name: NVIDIA RTX 4000 Ada Generation
Reported VRAM: 19 GB
Hourly amount in source scope: USD $0.092/hr · Instance
Source billing unit: Instance-hour
12/24
128 GB
19 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 pageP40 24GB 1×
DE
USD (stablecoin) • platform fees may apply
$0.101 per GPU-hour
Minimum billable instance cost: USD $0.101/hr · Minimum billing duration unknown
Details & source
SKU: 123024 · Availability: Available · A · Official API
Reported GPU name: Tesla P40
Reported VRAM: 23 GB
Hourly amount in source scope: USD $0.101/hr · Instance
Source billing unit: Instance-hour
8/16
32 GB
23 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 pageP40 24GB 1×
DE
USD (stablecoin) • platform fees may apply
$0.101 per GPU-hour
Minimum billable instance cost: USD $0.101/hr · Minimum billing duration unknown
Details & source
SKU: 123024 · Availability: Available · A · Official API
Reported GPU name: Tesla P40
Reported VRAM: 23 GB
Hourly amount in source scope: USD $0.101/hr · Instance
Source billing unit: Instance-hour
8/16
32 GB
23 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 pageQuadro RTX 6000 24GB 1×
US
USD (stablecoin) • platform fees may apply
$0.125 per GPU-hour
Minimum billable instance cost: USD $0.125/hr · Minimum billing duration unknown
Details & source
SKU: 123077 · Availability: Available · A · Official API
Reported GPU name: Quadro RTX 6000
Reported VRAM: 24 GB
Hourly amount in source scope: USD $0.125/hr · Instance
Source billing unit: Instance-hour
6/12
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 pageQuadro RTX 6000 24GB 1×
US
USD (stablecoin) • platform fees may apply
$0.154 per GPU-hour
Minimum billable instance cost: USD $0.154/hr · Minimum billing duration unknown
Details & source
SKU: 123077 · Availability: Available · A · Official API
Reported GPU name: Quadro RTX 6000
Reported VRAM: 24 GB
Hourly amount in source scope: USD $0.154/hr · Instance
Source billing unit: Instance-hour
6/12
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 pageRTX A4000 16GB 2×
RU
USD (stablecoin) • platform fees may apply
$0.079 per GPU-hour
Minimum billable instance cost: USD $0.158/hr · Minimum billing duration unknown
Details & source
SKU: 79417 · Availability: Available · A · Official API
Reported GPU name: NVIDIA RTX A4000
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.158/hr · Instance
Source billing unit: Instance-hour
64/128
256 GB
16 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 pageRTX 3080 10GB 2×
DE
USD (stablecoin) • platform fees may apply
$0.088 per GPU-hour
Minimum billable instance cost: USD $0.175/hr · Minimum billing duration unknown
Details & source
SKU: 104568 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3080
Reported VRAM: 10 GB
Hourly amount in source scope: USD $0.175/hr · Instance
Source billing unit: Instance-hour
4/4
16 GB
10 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 pageRTX 3080 10GB 2×
DE
USD (stablecoin) • platform fees may apply
$0.088 per GPU-hour
Minimum billable instance cost: USD $0.175/hr · Minimum billing duration unknown
Details & source
SKU: 104568 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3080
Reported VRAM: 10 GB
Hourly amount in source scope: USD $0.175/hr · Instance
Source billing unit: Instance-hour
4/4
16 GB
10 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 pageRTX 3090 24GB 2×
AR
USD (stablecoin) • platform fees may apply
$0.088 per GPU-hour
Minimum billable instance cost: USD $0.175/hr · Minimum billing duration unknown
Details & source
SKU: 92070 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3090
Reported VRAM: 24 GB
Hourly amount in source scope: USD $0.175/hr · Instance
Source billing unit: Instance-hour
2/2
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 pageRTX 4070 12GB 2×
CY
USD (stablecoin) • platform fees may apply
$0.092 per GPU-hour
Minimum billable instance cost: USD $0.185/hr · Minimum billing duration unknown
Details & source
SKU: 85809 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4070
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.185/hr · Instance
Source billing unit: Instance-hour
14/28
32 GB
12 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 pageRTX 4070 12GB 2×
CY
USD (stablecoin) • platform fees may apply
$0.092 per GPU-hour
Minimum billable instance cost: USD $0.185/hr · Minimum billing duration unknown
Details & source
SKU: 86004 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4070
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.185/hr · Instance
Source billing unit: Instance-hour
14/28
64 GB
12 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 pageRTX A4000 16GB 2×
RU
USD (stablecoin) • platform fees may apply
$0.094 per GPU-hour
Minimum billable instance cost: USD $0.188/hr · Minimum billing duration unknown
Details & source
SKU: 79417 · Availability: Available · A · Official API
Reported GPU name: NVIDIA RTX A4000
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.188/hr · Instance
Source billing unit: Instance-hour
64/128
256 GB
16 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 pageRTX PRO 2000 Blackwell 16GB 2×
IT
USD (stablecoin) • platform fees may apply
$0.094 per GPU-hour
Minimum billable instance cost: USD $0.188/hr · Minimum billing duration unknown
Details & source
SKU: 115304 · Availability: Available · A · Official API
Reported GPU name: NVIDIA RTX PRO 2000 Blackwell
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.188/hr · Instance
Source billing unit: Instance-hour
4/8
64 GB
16 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 pageRTX PRO 2000 Blackwell 16GB 2×
IT
USD (stablecoin) • platform fees may apply
$0.094 per GPU-hour
Minimum billable instance cost: USD $0.188/hr · Minimum billing duration unknown
Details & source
SKU: 115304 · Availability: Available · A · Official API
Reported GPU name: NVIDIA RTX PRO 2000 Blackwell
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.188/hr · Instance
Source billing unit: Instance-hour
4/8
64 GB
16 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 pageRTX 4090 24GB 1×
UA
USD (stablecoin) • platform fees may apply
$0.208 per GPU-hour
Minimum billable instance cost: USD $0.208/hr · Minimum billing duration unknown
Details & source
SKU: 118691 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4090
Reported VRAM: 24 GB
Hourly amount in source scope: USD $0.208/hr · Instance
Source billing unit: Instance-hour
16/32
64 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 pageRTX 3060 12GB 4×
RU
USD (stablecoin) • platform fees may apply
$0.052 per GPU-hour
Minimum billable instance cost: USD $0.208/hr · Minimum billing duration unknown
Details & source
SKU: 73682 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3060
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.208/hr · Instance
Source billing unit: Instance-hour
28/56
64 GB
12 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 pageRTX 3060 12GB 4×
RU
USD (stablecoin) • platform fees may apply
$0.052 per GPU-hour
Minimum billable instance cost: USD $0.208/hr · Minimum billing duration unknown
Details & source
SKU: 73682 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3060
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.208/hr · Instance
Source billing unit: Instance-hour
28/56
64 GB
12 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 pageRTX 4090 24GB 1×
UA
USD (stablecoin) • platform fees may apply
$0.212 per GPU-hour
Minimum billable instance cost: USD $0.212/hr · Minimum billing duration unknown
Details & source
SKU: 118691 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4090
Reported VRAM: 24 GB
Hourly amount in source scope: USD $0.212/hr · Instance
Source billing unit: Instance-hour
16/32
64 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 pageRTX 5070 12GB 2×
CY
USD (stablecoin) • platform fees may apply
$0.113 per GPU-hour
Minimum billable instance cost: USD $0.225/hr · Minimum billing duration unknown
Details & source
SKU: 92612 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5070
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.225/hr · Instance
Source billing unit: Instance-hour
14/28
64 GB
12 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 pageRTX 5070 12GB 2×
CY
USD (stablecoin) • platform fees may apply
$0.113 per GPU-hour
Minimum billable instance cost: USD $0.225/hr · Minimum billing duration unknown
Details & source
SKU: 110681 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5070
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.225/hr · Instance
Source billing unit: Instance-hour
28/56
64 GB
12 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 pageRTX 5060 Ti 16GB 2×
US
USD (stablecoin) • platform fees may apply
$0.115 per GPU-hour
Minimum billable instance cost: USD $0.229/hr · Minimum billing duration unknown
Details & source
SKU: 120386 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5060 Ti
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.229/hr · Instance
Source billing unit: Instance-hour
12/24
64 GB
16 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 pageRTX 5060 Ti 16GB 2×
US
USD (stablecoin) • platform fees may apply
$0.115 per GPU-hour
Minimum billable instance cost: USD $0.229/hr · Minimum billing duration unknown
Details & source
SKU: 120386 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5060 Ti
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.229/hr · Instance
Source billing unit: Instance-hour
12/24
64 GB
16 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 pageA100 PCIe 80GB 1×
US
USD (stablecoin) • platform fees may apply
$0.250 per GPU-hour
Minimum billable instance cost: USD $0.250/hr · Minimum billing duration unknown
Details & source
SKU: 124543 · Availability: Available · A · Official API
Reported GPU name: NVIDIA A100 80GB PCIe
Reported VRAM: 80 GB
Hourly amount in source scope: USD $0.250/hr · Instance
Source billing unit: Instance-hour
24/24
216 GB
80 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 pageRTX 5090 32GB 1×
NL
USD (stablecoin) • platform fees may apply
$0.250 per GPU-hour
Minimum billable instance cost: USD $0.250/hr · Minimum billing duration unknown
Details & source
SKU: 121170 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5090
Reported VRAM: 32 GB
Hourly amount in source scope: USD $0.250/hr · Instance
Source billing unit: Instance-hour
24/24
128 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 pageRTX 3060 Ti 8GB 4×
RU
USD (stablecoin) • platform fees may apply
$0.062 per GPU-hour
Minimum billable instance cost: USD $0.250/hr · Minimum billing duration unknown
Details & source
SKU: 93361 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3060 Ti
Reported VRAM: 8 GB
Hourly amount in source scope: USD $0.250/hr · Instance
Source billing unit: Instance-hour
12/24
16 GB
8 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 pageRTX 3060 Ti 8GB 4×
RU
USD (stablecoin) • platform fees may apply
$0.062 per GPU-hour
Minimum billable instance cost: USD $0.250/hr · Minimum billing duration unknown
Details & source
SKU: 93361 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3060 Ti
Reported VRAM: 8 GB
Hourly amount in source scope: USD $0.250/hr · Instance
Source billing unit: Instance-hour
12/24
16 GB
8 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 pageRTX 4080 SUPER 16GB 2×
US
USD (stablecoin) • platform fees may apply
$0.133 per GPU-hour
Minimum billable instance cost: USD $0.267/hr · Minimum billing duration unknown
Details & source
SKU: 115040 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4080 SUPER
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.267/hr · Instance
Source billing unit: Instance-hour
52/104
128 GB
16 GB
Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Clore's own USD conversion; not independently verified FX.
API record pageRTX 4070 Ti SUPER 16GB 2×
EG
USD (stablecoin) • platform fees may apply
$0.133 per GPU-hour
Minimum billable instance cost: USD $0.267/hr · Minimum billing duration unknown
Details & source
SKU: 117948 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4070 Ti SUPER
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.267/hr · Instance
Source billing unit: Instance-hour
14/28
64 GB
16 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 pageRTX 3070 8GB 4×
NZ
USD (stablecoin) • platform fees may apply
$0.068 per GPU-hour
Minimum billable instance cost: USD $0.271/hr · Minimum billing duration unknown
Details & source
SKU: 114341 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3070
Reported VRAM: 8 GB
Hourly amount in source scope: USD $0.271/hr · Instance
Source billing unit: Instance-hour
2/2
4 GB
8 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 pageRTX 3070 8GB 4×
NZ
USD (stablecoin) • platform fees may apply
$0.068 per GPU-hour
Minimum billable instance cost: USD $0.271/hr · Minimum billing duration unknown
Details & source
SKU: 114341 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3070
Reported VRAM: 8 GB
Hourly amount in source scope: USD $0.271/hr · Instance
Source billing unit: Instance-hour
2/2
4 GB
8 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 pageV100 SXM2 32GB 4×
RU
USD (stablecoin) • platform fees may apply
$0.074 per GPU-hour
Minimum billable instance cost: USD $0.295/hr · Minimum billing duration unknown
Details & source
SKU: 122717 · Availability: Available · A · Official API
Reported GPU name: Tesla V100SXM232GB
Reported VRAM: 32 GB
Hourly amount in source scope: USD $0.295/hr · Instance
Source billing unit: Instance-hour
24/48
192 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 pageV100 SXM2 32GB 4×
RU
USD (stablecoin) • platform fees may apply
$0.074 per GPU-hour
Minimum billable instance cost: USD $0.295/hr · Minimum billing duration unknown
Details & source
SKU: 122717 · Availability: Available · A · Official API
Reported GPU name: Tesla V100SXM232GB
Reported VRAM: 32 GB
Hourly amount in source scope: USD $0.295/hr · Instance
Source billing unit: Instance-hour
24/48
192 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 pageRTX 5070 Ti 16GB 2×
US
USD (stablecoin) • platform fees may apply
$0.155 per GPU-hour
Minimum billable instance cost: USD $0.310/hr · Minimum billing duration unknown
Details & source
SKU: 93280 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5070 Ti
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.310/hr · Instance
Source billing unit: Instance-hour
8/16
32 GB
16 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 pageRTX 4070 Ti SUPER 16GB 2×
EG
USD (stablecoin) • platform fees may apply
$0.156 per GPU-hour
Minimum billable instance cost: USD $0.312/hr · Minimum billing duration unknown
Details & source
SKU: 117948 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4070 Ti SUPER
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.312/hr · Instance
Source billing unit: Instance-hour
14/28
64 GB
16 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 pageRTX 5080 16GB 2×
UA
USD (stablecoin) • platform fees may apply
$0.157 per GPU-hour
Minimum billable instance cost: USD $0.315/hr · Minimum billing duration unknown
Details & source
SKU: 120876 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5080
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.315/hr · Instance
Source billing unit: Instance-hour
16/32
64 GB
16 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 pageRTX 3080 Ti 12GB 2×
KZ
USD (stablecoin) • platform fees may apply
$0.167 per GPU-hour
Minimum billable instance cost: USD $0.333/hr · Minimum billing duration unknown
Details & source
SKU: 115337 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3080 Ti
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.333/hr · Instance
Source billing unit: Instance-hour
14/28
8 GB
12 GB
Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Clore's own USD conversion; not independently verified FX.
API record pageRTX 2080 Ti 11GB 2×
UA
USD (stablecoin) • platform fees may apply
$0.167 per GPU-hour
Minimum billable instance cost: USD $0.333/hr · Minimum billing duration unknown
Details & source
SKU: 118505 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 2080 Ti
Reported VRAM: 11 GB
Hourly amount in source scope: USD $0.333/hr · Instance
Source billing unit: Instance-hour
14/28
32 GB
11 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 pageRTX 2080 Ti 11GB 2×
UA
USD (stablecoin) • platform fees may apply
$0.167 per GPU-hour
Minimum billable instance cost: USD $0.333/hr · Minimum billing duration unknown
Details & source
SKU: 118505 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 2080 Ti
Reported VRAM: 11 GB
Hourly amount in source scope: USD $0.333/hr · Instance
Source billing unit: Instance-hour
14/28
32 GB
11 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 pageRTX 3080 12GB 2×
CN
USD (stablecoin) • platform fees may apply
$0.167 per GPU-hour
Minimum billable instance cost: USD $0.333/hr · Minimum billing duration unknown
Details & source
SKU: 107310 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3080
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.333/hr · Instance
Source billing unit: Instance-hour
12/24
32 GB
12 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 pageRTX 3080 Ti 12GB 2×
UA
USD (stablecoin) • platform fees may apply
$0.167 per GPU-hour
Minimum billable instance cost: USD $0.333/hr · Minimum billing duration unknown
Details & source
SKU: 118118 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3080 Ti
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.333/hr · Instance
Source billing unit: Instance-hour
14/28
32 GB
12 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 pageL4 24GB 4×
US
USD (stablecoin) • platform fees may apply
$0.083 per GPU-hour
Minimum billable instance cost: USD $0.333/hr · Minimum billing duration unknown
Details & source
SKU: 119343 · Availability: Available · A · Official API
Reported GPU name: NVIDIA L4
Reported VRAM: 23 GB
Hourly amount in source scope: USD $0.333/hr · Instance
Source billing unit: Instance-hour
24/48
192 GB
23 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 pageRTX 3080 10GB 4×
LT
USD (stablecoin) • platform fees may apply
$0.083 per GPU-hour
Minimum billable instance cost: USD $0.333/hr · Minimum billing duration unknown
Details & source
SKU: 115408 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3080
Reported VRAM: 10 GB
Hourly amount in source scope: USD $0.333/hr · Instance
Source billing unit: Instance-hour
36/72
48 GB
10 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 pageRTX 5090 D v2 24GB 1×
HK
USD (stablecoin) • platform fees may apply
$0.338 per GPU-hour
Minimum billable instance cost: USD $0.338/hr · Minimum billing duration unknown
Details & source
SKU: 121049 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5090 D v2
Reported VRAM: 24 GB
Hourly amount in source scope: USD $0.338/hr · Instance
Source billing unit: Instance-hour
8/8
32 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 pageA30 24GB 1×
vCPU: 16
Region not specified by provider
$0.350 per GPU-hour
Minimum billable instance cost: USD $0.350/hr · Minimum billing duration unknown
Details & source
SKU: A30 (24GB) | 1 GPU | 256 storage · Availability: Unknown · C · Display only
Reported GPU name: A30 (24GB)
Reported VRAM: 24GB
Hourly amount in source scope: USD $0.350/hr · Instance
Source billing unit: Instance-hour
48 GB
24GB
A100 PCIe 80GB 1×
US
USD (stablecoin) • platform fees may apply
$0.354 per GPU-hour
Minimum billable instance cost: USD $0.354/hr · Minimum billing duration unknown
Details & source
SKU: 124543 · Availability: Available · A · Official API
Reported GPU name: NVIDIA A100 80GB PCIe
Reported VRAM: 80 GB
Hourly amount in source scope: USD $0.354/hr · Instance
Source billing unit: Instance-hour
24/24
216 GB
80 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 pageRTX 5080 16GB 2×
UA
USD (stablecoin) • platform fees may apply
$0.187 per GPU-hour
Minimum billable instance cost: USD $0.375/hr · Minimum billing duration unknown
Details & source
SKU: 120876 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5080
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.375/hr · Instance
Source billing unit: Instance-hour
16/32
64 GB
16 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 pageRTX 3080 10GB 4×
BE
USD (stablecoin) • platform fees may apply
$0.094 per GPU-hour
Minimum billable instance cost: USD $0.375/hr · Minimum billing duration unknown
Details & source
SKU: 119800 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3080
Reported VRAM: 10 GB
Hourly amount in source scope: USD $0.375/hr · Instance
Source billing unit: Instance-hour
2/2
16 GB
10 GB
Listed whole-server daily price divided by 24 and GPU count. Platform service fees may apply; tax treatment unknown. Clore's own USD conversion; not independently verified FX.
API record pageRTX 3090 20GB 1×
UA
USD (stablecoin) • platform fees may apply
$0.375 per GPU-hour
Minimum billable instance cost: USD $0.375/hr · Minimum billing duration unknown
Details & source
SKU: 118409 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3090
Reported VRAM: 20 GB
Hourly amount in source scope: USD $0.375/hr · Instance
Source billing unit: Instance-hour
12/24
16 GB
20 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 pageRTX 3090 20GB 1×
UA
USD (stablecoin) • platform fees may apply
$0.375 per GPU-hour
Minimum billable instance cost: USD $0.375/hr · Minimum billing duration unknown
Details & source
SKU: 118409 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3090
Reported VRAM: 20 GB
Hourly amount in source scope: USD $0.375/hr · Instance
Source billing unit: Instance-hour
12/24
16 GB
20 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 pageRTX 3080 12GB 2×
CN
USD (stablecoin) • platform fees may apply
$0.188 per GPU-hour
Minimum billable instance cost: USD $0.375/hr · Minimum billing duration unknown
Details & source
SKU: 107310 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3080
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.375/hr · Instance
Source billing unit: Instance-hour
12/24
32 GB
12 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 pageRTX 4070 SUPER 12GB 2×
RU
USD (stablecoin) • platform fees may apply
$0.188 per GPU-hour
Minimum billable instance cost: USD $0.375/hr · Minimum billing duration unknown
Details & source
SKU: 119568 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4070 SUPER
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.375/hr · Instance
Source billing unit: Instance-hour
14/28
32 GB
12 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 pageRTX 4070 SUPER 12GB 2×
RU
USD (stablecoin) • platform fees may apply
$0.188 per GPU-hour
Minimum billable instance cost: USD $0.375/hr · Minimum billing duration unknown
Details & source
SKU: 119568 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4070 SUPER
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.375/hr · Instance
Source billing unit: Instance-hour
14/28
32 GB
12 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 pageRTX 5070 Ti 16GB 2×
NO
USD (stablecoin) • platform fees may apply
$0.188 per GPU-hour
Minimum billable instance cost: USD $0.375/hr · Minimum billing duration unknown
Details & source
SKU: 123603 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5070 Ti
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.375/hr · Instance
Source billing unit: Instance-hour
6/12
16 GB
16 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 pageRTX 5090 D v2 24GB 1×
HK
USD (stablecoin) • platform fees may apply
$0.377 per GPU-hour
Minimum billable instance cost: USD $0.377/hr · Minimum billing duration unknown
Details & source
SKU: 121049 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5090 D v2
Reported VRAM: 24 GB
Hourly amount in source scope: USD $0.377/hr · Instance
Source billing unit: Instance-hour
8/8
32 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 pageRTX 4070 Ti 12GB 2×
FI
USD (stablecoin) • platform fees may apply
$0.202 per GPU-hour
Minimum billable instance cost: USD $0.403/hr · Minimum billing duration unknown
Details & source
SKU: 116974 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4070 Ti
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.403/hr · Instance
Source billing unit: Instance-hour
8/16
64 GB
12 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 pageRTX 4070 Ti 12GB 2×
FI
USD (stablecoin) • platform fees may apply
$0.206 per GPU-hour
Minimum billable instance cost: USD $0.412/hr · Minimum billing duration unknown
Details & source
SKU: 116974 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4070 Ti
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.412/hr · Instance
Source billing unit: Instance-hour
8/16
64 GB
12 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 pageL4 24GB 4×
US
USD (stablecoin) • platform fees may apply
$0.104 per GPU-hour
Minimum billable instance cost: USD $0.417/hr · Minimum billing duration unknown
Details & source
SKU: 119343 · Availability: Available · A · Official API
Reported GPU name: NVIDIA L4
Reported VRAM: 23 GB
Hourly amount in source scope: USD $0.417/hr · Instance
Source billing unit: Instance-hour
24/48
192 GB
23 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 pageRTX 5060 Ti 7GB 4×
MY
USD (stablecoin) • platform fees may apply
$0.104 per GPU-hour
Minimum billable instance cost: USD $0.417/hr · Minimum billing duration unknown
Details & source
SKU: 123421 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5060 Ti
Reported VRAM: 7 GB
Hourly amount in source scope: USD $0.417/hr · Instance
Source billing unit: Instance-hour
64/128
219 GB
7 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 pageRTX 5060 Ti 7GB 4×
MY
USD (stablecoin) • platform fees may apply
$0.104 per GPU-hour
Minimum billable instance cost: USD $0.417/hr · Minimum billing duration unknown
Details & source
SKU: 123421 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5060 Ti
Reported VRAM: 7 GB
Hourly amount in source scope: USD $0.417/hr · Instance
Source billing unit: Instance-hour
64/128
219 GB
7 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 pageRTX 5070 12GB 4×
US
USD (stablecoin) • platform fees may apply
$0.114 per GPU-hour
Minimum billable instance cost: USD $0.456/hr · Minimum billing duration unknown
Details & source
SKU: 72251 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5070
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.456/hr · Instance
Source billing unit: Instance-hour
28/56
64 GB
12 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$0.458 per GPU-hour
Minimum billable instance cost: USD $0.458/hr · Minimum billing duration unknown
Details & source
SKU: 1A6000.10V · Availability: Unknown · A · Official API
Reported GPU name: 1x RTX A6000 48GB
Reported VRAM: 48GB GPU RAM
Hourly amount in source scope: USD $0.458/hr · Instance
Source billing unit: Instance-hour
10 CPU
60GB RAM
48GB GPU RAM
RTX 4080 16GB 2×
RU
USD (stablecoin) • platform fees may apply
$0.263 per GPU-hour
Minimum billable instance cost: USD $0.525/hr · Minimum billing duration unknown
Details & source
SKU: 119571 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4080
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.525/hr · Instance
Source billing unit: Instance-hour
14/28
32 GB
16 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 pageRTX 4080 16GB 2×
RU
USD (stablecoin) • platform fees may apply
$0.263 per GPU-hour
Minimum billable instance cost: USD $0.525/hr · Minimum billing duration unknown
Details & source
SKU: 119571 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4080
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.525/hr · Instance
Source billing unit: Instance-hour
14/28
32 GB
16 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 pageRTX 5070 Ti 16GB 4×
US
USD (stablecoin) • platform fees may apply
$0.135 per GPU-hour
Minimum billable instance cost: USD $0.539/hr · Minimum billing duration unknown
Details & source
SKU: 75434 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5070 Ti
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.539/hr · Instance
Source billing unit: Instance-hour
28/56
64 GB
16 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 pageRTX 5070 12GB 4×
BY
USD (stablecoin) • platform fees may apply
$0.136 per GPU-hour
Minimum billable instance cost: USD $0.542/hr · Minimum billing duration unknown
Details & source
SKU: 120604 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5070
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.542/hr · Instance
Source billing unit: Instance-hour
6/12
8 GB
12 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 pageRTX A6000 48GB 1×
vCPU: 6
Region not specified by provider
$0.550 per GPU-hour
Minimum billable instance cost: USD $0.550/hr · Minimum billing duration unknown
Details & source
SKU: RTX A6000 (48GB) [ALT Config] | 1 GPU | 256 storage · Availability: Unknown · C · Display only
Reported GPU name: RTX A6000 (48GB) [ALT Config]
Reported VRAM: 48GB
Hourly amount in source scope: USD $0.550/hr · Instance
Source billing unit: Instance-hour
32 GB
48GB
$0.591 per GPU-hour
Minimum billable instance cost: USD $0.591/hr · Minimum billing duration unknown
Details & source
SKU: Standard_NV36ads_A10_v5 · Availability: Unknown · A · Official API
Reported GPU name: A10 24GB
Hourly amount in source scope: USD $0.591/hr · Instance
Source billing unit: Instance-hour
RTX 4070 Ti 12GB 4×
RU
USD (stablecoin) • platform fees may apply
$0.156 per GPU-hour
Minimum billable instance cost: USD $0.625/hr · Minimum billing duration unknown
Details & source
SKU: 112607 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4070 Ti
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.625/hr · Instance
Source billing unit: Instance-hour
14/28
64 GB
12 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 pageRTX 4070 Ti 12GB 4×
RU
USD (stablecoin) • platform fees may apply
$0.156 per GPU-hour
Minimum billable instance cost: USD $0.625/hr · Minimum billing duration unknown
Details & source
SKU: 112607 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4070 Ti
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.625/hr · Instance
Source billing unit: Instance-hour
14/28
64 GB
12 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 pageRTX 4080 SUPER 16GB 2×
CN
USD (stablecoin) • platform fees may apply
$0.333 per GPU-hour
Minimum billable instance cost: USD $0.667/hr · Minimum billing duration unknown
Details & source
SKU: 107786 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 4080 SUPER
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.667/hr · Instance
Source billing unit: Instance-hour
96/192
96 GB
16 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 pageRTX 5070 Ti 16GB 4×
AU
USD (stablecoin) • platform fees may apply
$0.173 per GPU-hour
Minimum billable instance cost: USD $0.691/hr · Minimum billing duration unknown
Details & source
SKU: 120030 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5070 Ti
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.691/hr · Instance
Source billing unit: Instance-hour
2/2
8 GB
16 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 pageRTX PRO 4000 Blackwell 24GB 4×
RU
USD (stablecoin) • platform fees may apply
$0.188 per GPU-hour
Minimum billable instance cost: USD $0.750/hr · Minimum billing duration unknown
Details & source
SKU: 120315 · Availability: Available · A · Official API
Reported GPU name: NVIDIA RTX PRO 4000 Blackwell
Reported VRAM: 24 GB
Hourly amount in source scope: USD $0.750/hr · Instance
Source billing unit: Instance-hour
56/112
512 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 pageRTX 6000 Ada 48GB 1×
vCPU: 12
Region not specified by provider
$0.790 per GPU-hour
Minimum billable instance cost: USD $0.790/hr · Minimum billing duration unknown
Details & source
SKU: RTX 6000 ADA (48GB) | 1 GPU | 350 storage · Availability: Unknown · C · Display only
Reported GPU name: RTX 6000 ADA (48GB)
Reported VRAM: 48GB
Hourly amount in source scope: USD $0.790/hr · Instance
Source billing unit: Instance-hour
72 GB
48GB
RTX 6000 Ada 48GB 1×
Region not specified by provider
$0.827 per GPU-hour
Minimum billable instance cost: USD $0.827/hr · Minimum billing duration unknown
Details & source
SKU: 1RTX6000ADA.10V · Availability: Unknown · A · Official API
Reported GPU name: 1x RTX 6000 Ada 48GB
Reported VRAM: 48GB GPU RAM
Hourly amount in source scope: USD $0.827/hr · Instance
Source billing unit: Instance-hour
10 CPU
60GB RAM
48GB GPU RAM
RTX 3080 Ti 12GB 4×
MY
USD (stablecoin) • platform fees may apply
$0.208 per GPU-hour
Minimum billable instance cost: USD $0.833/hr · Minimum billing duration unknown
Details & source
SKU: 91725 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3080 Ti
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.833/hr · Instance
Source billing unit: Instance-hour
2/2
4 GB
12 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 pageRTX 3080 Ti 12GB 4×
MY
USD (stablecoin) • platform fees may apply
$0.208 per GPU-hour
Minimum billable instance cost: USD $0.833/hr · Minimum billing duration unknown
Details & source
SKU: 91725 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3080 Ti
Reported VRAM: 12 GB
Hourly amount in source scope: USD $0.833/hr · Instance
Source billing unit: Instance-hour
2/2
4 GB
12 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 pageRTX PRO 4000 Blackwell 24GB 4×
RU
USD (stablecoin) • platform fees may apply
$0.208 per GPU-hour
Minimum billable instance cost: USD $0.833/hr · Minimum billing duration unknown
Details & source
SKU: 120315 · Availability: Available · A · Official API
Reported GPU name: NVIDIA RTX PRO 4000 Blackwell
Reported VRAM: 24 GB
Hourly amount in source scope: USD $0.833/hr · Instance
Source billing unit: Instance-hour
56/112
512 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$0.835 per GPU-hour
Original hourly price: EUR 0.76/hr · Instance
Minimum billable instance cost: USD $0.835/hr · Initial billing minimum: USD $0.014 / 60 seconds
Details & source
SKU: a10-45.consumption · Availability: Unknown · A · Official API
Reported GPU name: A10
Reported VRAM: 24 GB/GPU
Hourly amount in source scope: USD $0.835/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
Original hourly price: EUR 0.76 · USD conversion rate: 1.0989 · ECB 2026-11-17
42 GB
24 GB/GPU
FR subsidiary base Linux public-cloud catalog; exact region and capacity unspecified; local/3-AZ prices not inferred.
API record pageL40 48GB 1×
vCPU: 14
Region not specified by provider
$0.860 per GPU-hour
Minimum billable instance cost: USD $0.860/hr · Minimum billing duration unknown
Details & source
SKU: L40 (48GB) | 1 GPU | 625 storage · Availability: Unknown · C · Display only
Reported GPU name: L40 (48GB)
Reported VRAM: 48GB
Hourly amount in source scope: USD $0.860/hr · Instance
Source billing unit: Instance-hour
72 GB
48GB
RTX PRO 6000 Blackwell Workstation 96GB 1×
MY
USD (stablecoin) • platform fees may apply
$0.875 per GPU-hour
Minimum billable instance cost: USD $0.875/hr · Minimum billing duration unknown
Details & source
SKU: 123341 · Availability: Available · A · Official API
Reported GPU name: NVIDIA RTX PRO 6000 Blackwell Workstation
Reported VRAM: 96 GB
Hourly amount in source scope: USD $0.875/hr · Instance
Source billing unit: Instance-hour
32/64
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 pageRTX PRO 6000 Blackwell Workstation 96GB 1×
MY
USD (stablecoin) • platform fees may apply
$0.875 per GPU-hour
Minimum billable instance cost: USD $0.875/hr · Minimum billing duration unknown
Details & source
SKU: 123341 · Availability: Available · A · Official API
Reported GPU name: NVIDIA RTX PRO 6000 Blackwell Workstation
Reported VRAM: 96 GB
Hourly amount in source scope: USD $0.875/hr · Instance
Source billing unit: Instance-hour
32/64
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 pageH100 NVL 94GB 2×
US
USD (stablecoin) • platform fees may apply
$0.458 per GPU-hour
Minimum billable instance cost: USD $0.917/hr · Minimum billing duration unknown
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 pageRTX 5080 16GB 4×
DE
USD (stablecoin) • platform fees may apply
$0.229 per GPU-hour
Minimum billable instance cost: USD $0.917/hr · Minimum billing duration unknown
Details & source
SKU: 85165 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5080
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.917/hr · Instance
Source billing unit: Instance-hour
64/128
256 GB
16 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 pageRTX 5080 16GB 4×
DE
USD (stablecoin) • platform fees may apply
$0.229 per GPU-hour
Minimum billable instance cost: USD $0.917/hr · Minimum billing duration unknown
Details & source
SKU: 85165 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5080
Reported VRAM: 16 GB
Hourly amount in source scope: USD $0.917/hr · Instance
Source billing unit: Instance-hour
64/128
256 GB
16 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 pageRTX PRO 4500 Blackwell 32GB 1×
vCPU: 16
Region not specified by provider
$0.920 per GPU-hour
Minimum billable instance cost: USD $0.920/hr · Minimum billing duration unknown
Details & source
SKU: RTX PRO 4500 Blackwell (32GB) | 1 GPU | 700 storage · Availability: Unknown · C · Display only
Reported GPU name: RTX PRO 4500 Blackwell (32GB)
Reported VRAM: 32GB
Hourly amount in source scope: USD $0.920/hr · Instance
Source billing unit: Instance-hour
74 GB
32GB
L40S 48GB 1×
vCPU: 12
Region not specified by provider
$0.970 per GPU-hour
Minimum billable instance cost: USD $0.970/hr · Minimum billing duration unknown
Details & source
SKU: L40S (48GB) | 1 GPU | 625 storage · Availability: Unknown · C · Display only
Reported GPU name: L40S (48GB)
Reported VRAM: 48GB
Hourly amount in source scope: USD $0.970/hr · Instance
Source billing unit: Instance-hour
72 GB
48GB
$1.01 per GPU-hour
Minimum billable instance cost: USD $1.01/hr · Initial billing minimum: USD $0.017 / 60 seconds
Details & source
SKU: g5.xlarge · Availability: Unknown · A · Official API
Reported GPU name: A10G
Reported VRAM: 24 GB
Hourly amount in source scope: USD $1.01/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
24 GB
Linux, shared tenancy, no preinstalled software; storage and data transfer extra.
API record pageRTX A5000 24GB 8×
ES
USD (stablecoin) • platform fees may apply
$0.142 per GPU-hour
Minimum billable instance cost: USD $1.13/hr · Minimum billing duration unknown
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 pageRTX A5000 24GB 8×
ES
USD (stablecoin) • platform fees may apply
$0.142 per GPU-hour
Minimum billable instance cost: USD $1.13/hr · Minimum billing duration unknown
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 pageA100 SXM4 40GB 2×
US
USD (stablecoin) • platform fees may apply
$0.583 per GPU-hour
Minimum billable instance cost: USD $1.17/hr · Minimum billing duration unknown
Details & source
SKU: 120846 · Availability: Available · A · Official API
Reported GPU name: NVIDIA A100SXM440GB
Reported VRAM: 40 GB
Hourly amount in source scope: USD $1.17/hr · Instance
Source billing unit: Instance-hour
12/24
167 GB
40 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$1.21 per GPU-hour
Minimum billable instance cost: USD $1.21/hr · Minimum billing duration unknown
Details & source
SKU: 1A100.22V · Availability: Unknown · A · Official API
Reported GPU name: 1x A100 SXM4 80GB
Reported VRAM: 80GB GPU RAM
Hourly amount in source scope: USD $1.21/hr · Instance
Source billing unit: Instance-hour
22 CPU
120GB RAM
80GB GPU RAM
$0.309 per GPU-hour
Minimum billable instance cost: USD $1.23/hr · Minimum billing duration unknown
Details & source
SKU: Standard_NC64as_T4_v3 · Availability: Unknown · A · Official API
Reported GPU name: T4 16GB
Hourly amount in source scope: USD $1.23/hr · Instance
Source billing unit: Instance-hour
RTX 3090 Ti 24GB 3×
HR
USD (stablecoin) • platform fees may apply
$0.417 per GPU-hour
Minimum billable instance cost: USD $1.25/hr · Minimum billing duration unknown
Details & source
SKU: 103372 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3090 Ti
Reported VRAM: 24 GB
Hourly amount in source scope: USD $1.25/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 pageRTX 3090 Ti 24GB 3×
HR
USD (stablecoin) • platform fees may apply
$0.417 per GPU-hour
Minimum billable instance cost: USD $1.25/hr · Minimum billing duration unknown
Details & source
SKU: 103372 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 3090 Ti
Reported VRAM: 24 GB
Hourly amount in source scope: USD $1.25/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 pageA100 80GB 1×
vCPU: 16
Region not specified by provider
$1.35 per GPU-hour
Minimum billable instance cost: USD $1.35/hr · Minimum billing duration unknown
Details & source
SKU: A100 (80GB) | 1 GPU | 512 storage · Availability: Unknown · C · Display only
Reported GPU name: A100 (80GB)
Reported VRAM: 80GB
Hourly amount in source scope: USD $1.35/hr · Instance
Source billing unit: Instance-hour
96 GB
80GB
$1.37 per GPU-hour
Original hourly price: CNY 9.1/hr · Instance
Minimum billable instance cost: USD $1.37/hr · Minimum billing duration unknown
Details & source
SKU: bcc.gn5.c16m64.1a10 · Availability: Unknown · C · Display only
Reported GPU name: 1*Nvidia A10 PCIE
Reported VRAM: 24GB
Hourly amount in source scope: USD $1.37/hr · Instance
Source billing unit: Instance-hour
Original hourly price: CNY 9.1 · USD conversion rate: 0.150012 · ECB 2026-11-17
16核
64GB
24GB
RTX 5090 32GB 4×
RU
USD (stablecoin) • platform fees may apply
$0.344 per GPU-hour
Minimum billable instance cost: USD $1.38/hr · Minimum billing duration unknown
Details & source
SKU: 78113 · Availability: Available · A · Official API
Reported GPU name: NVIDIA GeForce RTX 5090
Reported VRAM: 32 GB
Hourly amount in source scope: USD $1.38/hr · Instance
Source billing unit: Instance-hour
40/80
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 pageA100 SXM4 80GB 1×
vCPU: 14
Region not specified by provider
$1.38 per GPU-hour
Minimum billable instance cost: USD $1.38/hr · Minimum billing duration unknown
Details & source
SKU: A100 SXM4 (80GB) | 1 GPU | 625 storage · Availability: Unknown · C · Display only
Reported GPU name: A100 SXM4 (80GB)
Reported VRAM: 80GB
Hourly amount in source scope: USD $1.38/hr · Instance
Source billing unit: Instance-hour
100 GB
80GB
DGX A100 80GB 1×
vCPU: 16
Region not specified by provider
$1.38 per GPU-hour
Minimum billable instance cost: USD $1.38/hr · Minimum billing duration unknown
Details & source
SKU: DGX A100 (80GB) | 1 GPU | 1000 storage · Availability: Unknown · C · Display only
Reported GPU name: DGX A100 (80GB)
Reported VRAM: 80GB
Hourly amount in source scope: USD $1.38/hr · Instance
Source billing unit: Instance-hour
120 GB
80GB
RTX PRO 6000 96GB 1×
Region not specified by provider
$1.46 per GPU-hour
Minimum billable instance cost: USD $1.46/hr · Minimum billing duration unknown
Details & source
SKU: 1RTXPRO6000.30V · Availability: Unknown · A · Official API
Reported GPU name: 1x RTX PRO 6000 96GB
Reported VRAM: 96GB GPU RAM
Hourly amount in source scope: USD $1.46/hr · Instance
Source billing unit: Instance-hour
30 CPU
90GB RAM
96GB GPU RAM
RTX PRO 6000 CC 96GB 1×
Region not specified by provider
$1.49 per GPU-hour
Minimum billable instance cost: USD $1.49/hr · Minimum billing duration unknown
Details & source
SKU: 1RTXPRO6000.30V.CC · Availability: Unknown · A · Official API
Reported GPU name: 1x RTX PRO 6000 CC 96GB
Reported VRAM: 96GB GPU RAM
Hourly amount in source scope: USD $1.49/hr · Instance
Source billing unit: Instance-hour
30 CPU
90GB RAM
96GB GPU RAM
A100 SXM4 40GB 2×
US
USD (stablecoin) • platform fees may apply
$0.792 per GPU-hour
Minimum billable instance cost: USD $1.58/hr · Minimum billing duration unknown
Details & source
SKU: 120846 · Availability: Available · A · Official API
Reported GPU name: NVIDIA A100SXM440GB
Reported VRAM: 40 GB
Hourly amount in source scope: USD $1.58/hr · Instance
Source billing unit: Instance-hour
12/24
167 GB
40 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 pageH100 NVL 94GB 2×
US
USD (stablecoin) • platform fees may apply
$0.833 per GPU-hour
Minimum billable instance cost: USD $1.67/hr · Minimum billing duration unknown
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 pageH200 141GB 1×
US
USD (stablecoin) • platform fees may apply
$1.75 per GPU-hour
Minimum billable instance cost: USD $1.75/hr · Minimum billing duration unknown
Details & source
SKU: 123213 · Availability: Available · A · Official API
Reported GPU name: NVIDIA H200
Reported VRAM: 141 GB
Hourly amount in source scope: USD $1.75/hr · Instance
Source billing unit: Instance-hour
24/24
256 GB
141 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 pageH200 141GB 1×
US
USD (stablecoin) • platform fees may apply
$1.75 per GPU-hour
Minimum billable instance cost: USD $1.75/hr · Minimum billing duration unknown
Details & source
SKU: 123213 · Availability: Available · A · Official API
Reported GPU name: NVIDIA H200
Reported VRAM: 141 GB
Hourly amount in source scope: USD $1.75/hr · Instance
Source billing unit: Instance-hour
24/24
256 GB
141 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$1.04 per GPU-hour
Minimum billable instance cost: USD $2.08/hr · Minimum billing duration unknown
Details & source
SKU: 2L40S.40V · Availability: Unknown · A · Official API
Reported GPU name: 2x L40S 48GB
Reported VRAM: 96GB GPU RAM
Hourly amount in source scope: USD $2.08/hr · Instance
Source billing unit: Instance-hour
40 CPU
120GB RAM
96GB GPU RAM
RTX PRO 6000 Blackwell 96GB 1×
vCPU: 16
Region not specified by provider
$2.19 per GPU-hour
Minimum billable instance cost: USD $2.19/hr · Minimum billing duration unknown
Details & source
SKU: RTX PRO 6000 Blackwell (96GB) [Reduced Storage] | 1 GPU | 350 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 $2.19/hr · Instance
Source billing unit: Instance-hour
144 GB
96GB
$1.25 per GPU-hour
Original hourly price: CNY 16.6/hr · Instance
Minimum billable instance cost: USD $2.49/hr · Minimum billing duration unknown
Details & source
SKU: bcc.gn3.c40m160.2t4 · Availability: Unknown · C · Display only
Reported GPU name: 2 * NVIDIA Tesla T4
Reported VRAM: 32GB
Hourly amount in source scope: USD $2.49/hr · Instance
Source billing unit: Instance-hour
Original hourly price: CNY 16.6 · USD conversion rate: 0.150012 · ECB 2026-11-17
40核
160GB
32GB
$2.52 per GPU-hour
Minimum billable instance cost: USD $2.52/hr · Initial billing minimum: USD $0.042 / 60 seconds
Details & source
SKU: g7.2xlarge · Availability: Unknown · A · Official API
Reported GPU name: RTX PRO 4500
Reported VRAM: 32 GB
Hourly amount in source scope: USD $2.52/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
32 GB
Linux, shared tenancy, no preinstalled software; storage and data transfer extra.
API record pageH100 80GB 1×
vCPU: 20
Region not specified by provider
$2.73 per GPU-hour
Minimum billable instance cost: USD $2.73/hr · Minimum billing duration unknown
Details & source
SKU: H100 (80GB) | 1 GPU | 1250 storage · Availability: Unknown · C · Display only
Reported GPU name: H100 (80GB)
Reported VRAM: 80GB
Hourly amount in source scope: USD $2.73/hr · Instance
Source billing unit: Instance-hour
128 GB
80GB
RTX PRO 6000 96GB 1×
Region not specified by provider
$2.92 per GPU-hour
Minimum billable instance cost: USD $2.92/hr · Minimum billing duration unknown
Details & source
SKU: 1RTXPRO6000.30V · Availability: Unknown · A · Official API
Reported GPU name: 1x RTX PRO 6000 96GB
Reported VRAM: 96GB GPU RAM
Hourly amount in source scope: USD $2.92/hr · Instance
Source billing unit: Instance-hour
30 CPU
90GB RAM
96GB GPU RAM
RTX PRO 6000 CC 96GB 1×
Region not specified by provider
$2.98 per GPU-hour
Minimum billable instance cost: USD $2.98/hr · Minimum billing duration unknown
Details & source
SKU: 1RTXPRO6000.30V.CC · Availability: Unknown · A · Official API
Reported GPU name: 1x RTX PRO 6000 CC 96GB
Reported VRAM: 96GB GPU RAM
Hourly amount in source scope: USD $2.98/hr · Instance
Source billing unit: Instance-hour
30 CPU
90GB RAM
96GB GPU RAM
H100 NVL 1×
vCPU: 18
Region not specified by provider
$3.11 per GPU-hour
Minimum billable instance cost: USD $3.11/hr · Minimum billing duration unknown
Details & source
SKU: H100 NVL | 1 GPU | 750 storage · Availability: Unknown · C · Display only
Reported GPU name: H100 NVL
Hourly amount in source scope: USD $3.11/hr · Instance
Source billing unit: Instance-hour
128 GB
H100 SXM 80GB 1×
vCPU: 14
Region not specified by provider
$3.14 per GPU-hour
Minimum billable instance cost: USD $3.14/hr · Minimum billing duration unknown
Details & source
SKU: H100 SXM5 (80GB) | 1 GPU | 350 storage · Availability: Unknown · C · Display only
Reported GPU name: H100 SXM5 (80GB)
Reported VRAM: 80GB
Hourly amount in source scope: USD $3.14/hr · Instance
Source billing unit: Instance-hour
122 GB
80GB
$3.15 per GPU-hour
Original hourly price: EUR 2.8665/hr · Instance
Minimum billable instance cost: USD $3.15/hr · Minimum billing duration unknown
Details & source
SKU: /instance/server/h100_1_80g/fr-par-2 · Availability: Unknown · A · Official API
Reported GPU name: H100-PCIe
Hourly amount in source scope: USD $3.15/hr · Instance
Source billing unit: Instance-minute
Original hourly price: EUR 2.8665 · USD conversion rate: 1.0989 · ECB 2026-11-17
AMD EPYC 9334 (2.7 GHz), x64, vCPUs: 24
240 GiB
RTX PRO 6000 Blackwell Server Edition 96GB 1×
vCPU: 8 · RAM (GiB): 64
us-east-1
$3.36 per GPU-hour
Minimum billable instance cost: USD $3.36/hr · Initial billing minimum: USD $0.056 / 60 seconds
Details & source
SKU: g7e.2xlarge · Availability: Unknown · A · Official API
Reported GPU name: RTX PRO 6000 Blackwell Server Edition
Reported VRAM: 96 GB
Hourly amount in source scope: USD $3.36/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
96 GB
Linux, shared tenancy, no preinstalled software; storage and data transfer extra.
API record page$3.45 per GPU-hour
Minimum billable instance cost: USD $3.45/hr · Minimum billing duration unknown
Details & source
SKU: 1H200.141S.44V · Availability: Unknown · A · Official API
Reported GPU name: 1x H200 SXM5 141GB
Reported VRAM: 141GB GPU RAM
Hourly amount in source scope: USD $3.45/hr · Instance
Source billing unit: Instance-hour
44 CPU
170GB RAM
141GB GPU RAM
H200 NVL 141GB 1×
vCPU: 16
Region not specified by provider
$3.62 per GPU-hour
Minimum billable instance cost: USD $3.62/hr · Minimum billing duration unknown
Details & source
SKU: H200 NVL (141GB) | 1 GPU | 750 storage · Availability: Unknown · C · Display only
Reported GPU name: H200 NVL (141GB)
Reported VRAM: 141GB
Hourly amount in source scope: USD $3.62/hr · Instance
Source billing unit: Instance-hour
180 GB
141GB
$0.978 per GPU-hour
Minimum billable instance cost: USD $3.91/hr · Initial billing minimum: USD $0.065 / 60 seconds
Details & source
SKU: g4dn.12xlarge · Availability: Unknown · A · Official API
Reported GPU name: T4
Reported VRAM: 64 GB
Hourly amount in source scope: USD $3.91/hr · Instance
Source billing unit: Instance-hour
Minimum billing (seconds): 60
64 GB
Linux, shared tenancy, no preinstalled software; storage and data transfer extra.
API record page$0.509 per GPU-hour
Minimum billable instance cost: USD $4.07/hr · Minimum billing duration unknown
Details & source
SKU: Standard_ND40rs_v2 · Availability: Unknown · A · Official API
Reported GPU name: V100 32GB
Hourly amount in source scope: USD $4.07/hr · Instance
Source billing unit: Instance-hour
$2.33 per GPU-hour
Original hourly price: CNY 31.03/hr · Instance
Minimum billable instance cost: USD $4.65/hr · Minimum billing duration unknown
Details & source
SKU: bcc.gn3.c20m160.2v100-32g · Availability: Unknown · C · Display only
Reported GPU name: 2 * NVIDIA Tesla V100-32G
Reported VRAM: 64GB
Hourly amount in source scope: USD $4.65/hr · Instance
Source billing unit: Instance-hour
Original hourly price: CNY 31.03 · USD conversion rate: 0.150012 · ECB 2026-11-17
20核
160GB
64GB
$0.738 per GPU-hour
Minimum billable instance cost: USD $5.90/hr · Minimum billing duration unknown
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
$6.39 per GPU-hour
Minimum billable instance cost: USD $6.39/hr · Minimum billing duration unknown
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
$0.859 per GPU-hour
Minimum billable instance cost: USD $6.87/hr · Minimum billing duration unknown
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
GB300 SXM6 288GB 1×
Region not specified by provider
$7.35 per GPU-hour
Minimum billable instance cost: USD $7.35/hr · Minimum billing duration unknown
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
RTX PRO 6000 Blackwell MaxQ Works 96GB 4×
TW
USD (stablecoin) • platform fees may apply
$1.88 per GPU-hour
Minimum billable instance cost: USD $7.50/hr · Minimum billing duration unknown
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 pageRTX PRO 6000 Blackwell MaxQ Works 96GB 4×
TW
USD (stablecoin) • platform fees may apply
$1.88 per GPU-hour
Minimum billable instance cost: USD $7.50/hr · Minimum billing duration unknown
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$1.11 per GPU-hour
Minimum billable instance cost: USD $8.87/hr · Minimum billing duration unknown
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
$2.27 per GPU-hour
Minimum billable instance cost: USD $18.17/hr · Minimum billing duration unknown
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
B200 SXM6 180GB 2×
Region not specified by provider
$9.79 per GPU-hour
Minimum billable instance cost: USD $19.59/hr · Minimum billing duration unknown
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
$4.90 per GPU-hour
Minimum billable instance cost: USD $19.59/hr · Minimum billing duration unknown
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
B200 CC SXM6 180GB 2×
Region not specified by provider
$9.99 per GPU-hour
Minimum billable instance cost: USD $19.98/hr · Minimum billing duration unknown
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
B200 CC SXM6 180GB 4×
Region not specified by provider
$5.00 per GPU-hour
Minimum billable instance cost: USD $19.98/hr · Minimum billing duration unknown
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
$2.74 per GPU-hour
Minimum billable instance cost: USD $21.96/hr · Initial billing minimum: USD $0.366 / 60 seconds
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 pageB300 CC SXM6 268GB 4×
Region not specified by provider
$6.52 per GPU-hour
Minimum billable instance cost: USD $26.09/hr · Minimum billing duration unknown
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
$3.91 per GPU-hour
Original hourly price: CNY 208.67/hr · Instance
Minimum billable instance cost: USD $31.30/hr · Minimum billing duration unknown
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
$4.53 per GPU-hour
Original hourly price: CNY 241.43/hr · Instance
Minimum billable instance cost: USD $36.22/hr · Minimum billing duration unknown
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
$6.00 per GPU-hour
Minimum billable instance cost: USD $48.00/hr · Minimum billing duration unknown
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
B300 CC SXM6 268GB 4×
Region not specified by provider
$13.04 per GPU-hour
Minimum billable instance cost: USD $52.18/hr · Minimum billing duration unknown
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
H200 SXM5 141GB 8×
Region not specified by provider
$6.90 per GPU-hour
Minimum billable instance cost: USD $55.23/hr · Minimum billing duration unknown
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
GB300 SXM6 288GB 4×
Region not specified by provider
$14.71 per GPU-hour
Minimum billable instance cost: USD $58.83/hr · Minimum billing duration unknown
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
B300 SXM6 268GB 8×
Region not specified by provider
$12.79 per GPU-hour
Minimum billable instance cost: USD $102.30/hr · Minimum billing duration unknown
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
$14.00 per GPU-hour
Minimum billable instance cost: USD $112.00/hr · Minimum billing duration unknown
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$14.24 per GPU-hour
Minimum billable instance cost: USD $113.93/hr · Initial billing minimum: USD $1.90 / 60 seconds
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$17.80 per GPU-hour
Minimum billable instance cost: USD $142.42/hr · Initial billing minimum: USD $2.37 / 60 seconds
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 pageWhat to check before renting
- Test the exact model, precision, context or audio length and batch size; leave room for caches and temporary allocations.
- Confirm driver, CUDA compute capability or ROCm gfx target, framework and exact quantization kernels.
- Confirm CPU architecture: x86_64 versus aarch64, including container and wheel availability.
- Allow host RAM and disk for downloading and loading the weights, plus temporary files.
- For N > 1, confirm tensor-parallel engine support and GPU interconnect/topology; aggregate VRAM alone is insufficient.
- Check GPU count, minimum billable instance, billing duration, tax, FX, storage and egress. Plan request retries for interruptible Spot capacity.
- Recheck region access, quota and actual stock with the provider; an unknown availability label is not a reservation.
Official sources
- Hugging Face: official model card · https://huggingface.co/Qwen/Qwen2.5-7B-Instruct
- Hugging Face: official model configuration · https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/config.json
- Hugging Face: official BF16 weight index · https://huggingface.co/Qwen/Qwen2.5-7B-Instruct/blob/main/model.safetensors.index.json
- Qwen: speed and GPU-memory benchmark · https://qwen.readthedocs.io/en/v2.5/benchmark/speed_benchmark.html
- Qwen: benchmark memory calculation (bytes / 1024³) · https://github.com/QwenLM/Qwen2.5/blob/main/examples/speed-benchmark/speed_benchmark_transformers.py
- Hugging Face: official model configuration · DeepSeek-R1-Distill-Qwen-7B · https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B/blob/main/config.json
- Hugging Face: memory estimator and its inference caveats · https://huggingface.co/docs/accelerate/usage_guides/model_size_estimator
- vLLM: GPU installation and software floor · https://docs.vllm.ai/en/stable/getting_started/installation/gpu/
- vLLM: tensor-parallel serving · https://docs.vllm.ai/en/stable/serving/parallelism_scaling/
- PyTorch: stable CUDA release support matrix · https://github.com/pytorch/pytorch/blob/main/RELEASE.md#pytorch-cuda-support-matrix
Know the full job cost before you rent: GPU Budget Kit ($12)