NVIDIA B300 cloud prices
B300 on-demand cloud prices run from $9.50 to $17.80 per GPU-hour across 4 providers gpu.gl tracks (median $13.34). The lowest is Nebius.
Lowest price by provider
| Configuration | Where | Fetched | Source | |||
|---|---|---|---|---|---|---|
| Nebius | On-demand | $9.50 | HGX B300 · 1 GPU | Not stated per region | Nebius ↗ | |
| DataCrunch | On-demand | $11.69 | 1B300.30V · 1, 2, 4, 8 GPUs | Not stated per region | DataCrunch ↗ | |
| OCI | On-demand | $15.00 | B112237 (Compute - GPU - B300) · 1 GPU | All commercial regions | OCI ↗ | |
| AWS | On-demand | $17.80 | p6-b300.48xlarge · 8 GPUs | 2 regions | AWS ↗ | |
| DataCrunch | Spot / interruptible | $5.84 | 1B300.30V · 1, 2, 4, 8 GPUs | Not stated per region | DataCrunch ↗ | |
| DigitalOcean | Spot / interruptible | $6.17 | NVIDIA HGX B300 GPU Droplet · 1 GPU | Not stated per region | DigitalOcean ↗ | |
| DigitalOcean | Reserved 1 yr | $7.94 | NVIDIA HGX B300 GPU Droplet · 1 GPU | Not stated per region | DigitalOcean ↗ |
Price history
History starts 2026-11-08. gpu.gl stores one snapshot a day from launch and never back-fills, so a chart appears here once there are two daily snapshots with on-demand prices for this GPU (1 so far).
B300 specifications
The B300 has 270 GB of HBM3E and 7.7 TB/s of memory bandwidth. That is about 292 dense FP16 TFLOPS per TB/s of bandwidth; workloads that stream large weights, like LLM inference at small batch sizes, tend to be limited by the bandwidth figure, while large-batch training leans on the compute figure.
| Architecture | Blackwell Ultra |
|---|---|
| Memory | 270 GB HBM3E |
| Memory bandwidth | 7.7 TB/s |
| FP16 / BF16 tensor (dense) | 2,250 TFLOPS |
| FP8 tensor (dense) | 4,500 TFLOPS |
| Max power | 1100 W |
| Form factor | SXM |
Source: NVIDIA spec sheet. Tensor figures are dense (without sparsity). Per-GPU figures from the HGX B300 datasheet.
Every configuration
Each instance size or listing, at its cheapest region.
| Provider | Price type | $/GPU-hr | Instance | GPUs | Instance price | Cheapest region | Fetched | Source |
|---|---|---|---|---|---|---|---|---|
| Nebius | On-demand | $9.50 | HGX B300 | 1 | $9.50 per GPU-hour | Not stated per region | Nebius ↗ | |
| DataCrunch | On-demand | $11.69 | 1B300.30V | 1 | $11.69/hr | Not stated per region | DataCrunch ↗ | |
| DataCrunch | On-demand | $11.69 | 2B300.60V | 2 | $23.38/hr | Not stated per region | DataCrunch ↗ | |
| DataCrunch | On-demand | $11.69 | 4B300.120V | 4 | $46.76/hr | Not stated per region | DataCrunch ↗ | |
| DataCrunch | On-demand | $11.69 | 8B300.240V | 8 | $93.52/hr | Not stated per region | DataCrunch ↗ | |
| OCI | On-demand | $15.00 | B112237 (Compute - GPU - B300) | 1 | $15.00 per GPU-hour | All commercial regions | OCI ↗ | |
| AWS | On-demand | $17.80 | p6-b300.48xlarge | 8 | $142.42/hr | US East (N. Virginia) +1 more | AWS ↗ | |
| DataCrunch | Spot / interruptible | $5.84 | 1B300.30V | 1 | $5.85/hr | Not stated per region | DataCrunch ↗ | |
| DataCrunch | Spot / interruptible | $5.84 | 2B300.60V | 2 | $11.69/hr | Not stated per region | DataCrunch ↗ | |
| DataCrunch | Spot / interruptible | $5.84 | 4B300.120V | 4 | $23.38/hr | Not stated per region | DataCrunch ↗ | |
| DataCrunch | Spot / interruptible | $5.84 | 8B300.240V | 8 | $46.76/hr | Not stated per region | DataCrunch ↗ | |
| DigitalOcean | Spot / interruptible | $6.17 | NVIDIA HGX B300 GPU Droplet | 1 | $6.17 per GPU-hour | Not stated per region | DigitalOcean ↗ | |
| DigitalOcean | Reserved 1 yr | $7.94 | NVIDIA HGX B300 GPU Droplet | 1 | $7.94 per GPU-hour | Not stated per region | DigitalOcean ↗ |