Now offering crypto payments →

GPU Cloud Pricing · Blackwell Ultra

B300 Cloud Pricing

NVIDIA's flagship Blackwell Ultra accelerator: 288 GB of HBM3e per GPU, built for trillion-parameter training and long-context inference.

Out of stock
Live pricing

B300 price per GPU-hour

GPU.ai rates are the live fleet floor — the cheapest provider with stock, passed through at cost. Competitor rates are public on-demand list prices.

Provider$ / GPU / hr
GPU.ai — Secure CloudOut of stock
CoreWeaveNot available
AWS$17.80
AzureNot available

How these prices are computed

GPU.ai prices are read live from our aggregated fleet of 12+ GPU clouds and normalized to a per-GPU hourly rate (a multi-GPU node's price is divided by its GPU count). We charge the provider's raw rate with zero markup and bill per second. Competitor figures are each provider's public on-demand list rate for the closest equivalent SKU — never spot, reserved, or committed-use discounts. Stock counts reflect launchable inventory, not theoretical capacity. Last updated 2026-08-17; this page refreshes hourly.

Specifications

NVIDIA B300 (Blackwell Ultra) specs

ArchitectureBlackwell Ultra
VRAM288 GB HBM3e
Memory bandwidth8,000 GB/s
FP16 tensor (dense)
CUDA cores
Power (TDP)
InterconnectNVLink 5 (1.8 TB/s)
Released2025
What fits

What runs on 288 GB?

Minimum B300 count needed to hold popular open models in VRAM, at FP16 and 4-bit quantization.

ModelParamsFP164-bit
Llama 3.1 8B8B1× B3001× B300
Mistral 7B7B1× B3001× B300
Gemma 2 27B27B1× B3001× B300
Qwen2.5 32B32B1× B3001× B300
Llama 3.1 70B70B1× B3001× B300
Qwen2.5 72B72B1× B3001× B300
Mixtral 8x22B141B MoE2× B3001× B300
Llama 3.1 405B405B4× B3001× B300
FLUX.1 dev12B1× B3001× B300
SDXL3.5B1× B3001× B300
Whisper large-v31.5B1× B3001× B300

Weights-only estimates with a 20% margin for KV cache and activations at moderate context. Long contexts, large batches, and training need substantially more memory.

FAQ

B300 rental questions

How much does it cost to rent a B300 in the cloud?

B300 capacity is temporarily out of stock on GPU.ai. When available, pricing is the provider's raw rate with zero markup, billed per second. Check this page again — stock and prices refresh continuously.

How much VRAM does the B300 have?

The NVIDIA B300 (Blackwell Ultra) has 288 GB of HBM3e memory with up to 8,000 GB/s of bandwidth. GPU.ai reports the minimum VRAM actually delivered across our fleet, so the figure you see at launch is the figure you get.

How does GPU.ai's B300 pricing compare to AWS, Azure, and CoreWeave?

GPU.ai aggregates a dozen-plus GPU clouds and passes through each provider's raw price with no markup, so the same silicon is typically far cheaper than hyperscaler list rates. The comparison table on this page shows the current public on-demand list prices side by side.

How does billing work?

Billing is per second, starting when your instance is SSH-ready and stopping the moment you terminate. There are no minimum commitments, no reservation fees, and no egress surprises — you pay the listed hourly rate pro-rated to the second.