NVIDIA B200 cloud GPU prices
Compare B200 GPU rentals with whole-instance costs, region and pricing type visible together. Newer accelerators should be evaluated on completed-work cost as well as hourly price.
Rates dated Nov 10, 2026–Nov 10, 2026
Publication dates, not live quotes. Confirm the current rate and capacity with the provider.
Catalog generated .
Lowest listed on-demand rate
$6.69/GPU·hr
Lambda · B200 · SXM6 · 180 GB per GPU · 8 GPUs · $53.52/instance·hr · asia-northeast-1
Lowest listed spot / interruptible rate
$1.74/GPU·hr
Google Cloud · B200 · Unspecified · 180 GB per GPU · 8 GPUs · $13.92/instance·hr · asia-south2-c
Compare rental prices
Lowest listed compute rates. Explore comparison filters for your region.
| Provider / GPU / variant | VRAM per GPU | Pricing | Per GPU / hr | Full instance / hr | Region | Provider / rate date |
|---|---|---|---|---|---|---|
| Google Cloud B200 · Unspecified Instance: a4-highgpu-8g Link to offer | 180 GB | Spot / interruptible | $1.74 | $13.92 8 GPUs | asia-south2-c Stock unknown Stock & project cost | Check provider priceRate dated |
| Nebius B200 · SXM Instance: gpu-b200-sxm-a 1gpu-20vcpu-224gb Link to offer | 180 GB | Spot / interruptible | $1.90 | $1.90 1 GPUs | me-west1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Nebius B200 · SXM Instance: gpu-b200-sxm-a 8gpu-160vcpu-1792gb Link to offer | 180 GB | Spot / interruptible | $1.90 | $15.20 8 GPUs | me-west1 Stock unknown Stock & project cost | Check provider priceRate dated |
| AWS B200 · Unspecified Instance: p6-b200.48xlarge Link to offer | 180 GB | Spot / interruptible | $2.74 | $21.88 8 GPUs | eu-north-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch B200 · Unspecified Instance: 8B200.240V Link to offer | 180 GB | Spot / interruptible | $4.57 | $36.55 8 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch B200 · Unspecified Instance: 1B200.30V Link to offer | 180 GB | Spot / interruptible | $4.57 | $4.57 1 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch B200 · Unspecified Instance: 2B200.60V Link to offer | 180 GB | Spot / interruptible | $4.57 | $9.14 2 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch B200 · Unspecified Instance: 4B200.120V Link to offer | 180 GB | Spot / interruptible | $4.57 | $18.28 4 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| Lambda B200 · SXM6 Instance: gpu_8x_b200_sxm6 Link to offer | 180 GB | On-demand | $6.69 | $53.52 8 GPUs | asia-northeast-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Lambda B200 · SXM6 Instance: gpu_2x_b200_sxm6 Link to offer | 180 GB | On-demand | $6.89 | $13.78 2 GPUs | asia-northeast-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Lambda B200 · SXM6 Instance: gpu_1x_b200_sxm6 Link to offer | 180 GB | On-demand | $6.99 | $6.99 1 GPUs | asia-northeast-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| RunPod B200 · Unspecified Instance: NVIDIA B200 Link to offer | 180 GB | On-demand | $7.99 | $7.99 1 GPUs | EU-RO-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Nebius B200 · SXM Instance: gpu-b200-sxm-a 1gpu-20vcpu-224gb Link to offer | 180 GB | On-demand | $8.50 | $8.50 1 GPUs | me-west1 Stock unknown Stock & project cost | Check provider priceRate dated |
| Nebius B200 · SXM Instance: gpu-b200-sxm-a 8gpu-160vcpu-1792gb Link to offer | 180 GB | On-demand | $8.50 | $68.00 8 GPUs | me-west1 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch B200 · Unspecified Instance: 4B200.120V Link to offer | 180 GB | On-demand | $9.14 | $36.55 4 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch B200 · Unspecified Instance: 8B200.240V Link to offer | 180 GB | On-demand | $9.14 | $73.10 8 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch B200 · Unspecified Instance: 1B200.30V Link to offer | 180 GB | On-demand | $9.14 | $9.14 1 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| DataCrunch B200 · Unspecified Instance: 2B200.60V Link to offer | 180 GB | On-demand | $9.14 | $18.28 2 GPUs | FIN-01 Stock unknown Stock & project cost | Check provider priceRate dated |
| Google Cloud B200 · Unspecified Instance: a4-highgpu-8g Link to offer | 180 GB | On-demand | $11.28 | $90.22 8 GPUs | asia-northeast1-b Stock unknown Stock & project cost | Check provider priceRate dated |
| Oracle Cloud B200 · Unspecified Instance: BM.GPU.B200.8 Link to offer | 180 GB | On-demand | $14.00 | $112 8 GPUs | af-casablanca-1 Stock unknown Stock & project cost | Check provider priceRate dated |
| AWS B200 · Unspecified Instance: p6-b200.48xlarge Link to offer | 180 GB | On-demand | $14.24 | $114 8 GPUs | us-east-1 Stock unknown Stock & project cost | Check provider priceRate dated |
Manufacturer specifications, with conditions
Reviewed September 26, 2026 against NVIDIA documentation. These are hardware specifications and theoretical peaks, not NVGPU measurements or third-party benchmark results. Sparse Tensor Core peaks require supported structured sparsity; they are not expected dense training throughput.
| Reference variant | Memory | Memory bandwidth | FP16 Tensor Core peak | Conditions and source |
|---|---|---|---|---|
| B200 SXM | 180 GB HBM3e | Up to 8 TB/s | Not compared here | HGX reference configuration; do not apply it to GB200 or other Blackwell products. Verify framework support and the exact rental configuration. NVIDIA source |
NVGPU has not run application benchmarks for these comparisons. To assess a third-party result, require the model and revision, precision, batch size, sequence lengths, GPU count and variant, software versions, interconnect, test date and methodology.
Before you rent
- Check framework, driver and container compatibility before migrating a workload.
- Confirm GPU interconnect, networking and cluster capacity for multi-node training.
- Budget for the full instance shown in the table, plus separately billed storage and transfer.
What is included?
These are listed compute rates. The instance shown is the configuration being priced, not evidence of the provider's smallest available rental. Storage, data transfer, tax, licenses and support can be additional. Reserved contracts, commitment discounts and serverless per-request charges are not compared. Listed spot capacity can disappear or be interrupted.
Hourly price vs. total cost
Multiply the full-instance hourly rate by billed hours, then add storage, transfer and other charges. Compare the same workload and quality target. Rental throughput and uptime have not been measured by NVGPU.