B300 vs H100

The H100 is widely available across providers at a much lower hourly rate, while the B300 targets the largest training and inference jobs where per-GPU memory is the constraint.

Jump to: Specs Pricing Offers Similar GPUs

Overview

Nvidia B300

Highest VRAM in the Blackwell lineup for training the largest foundation models.

High Performance Datacenter

Nvidia H100

The standard data center GPU for large-scale AI training and inference.

High Performance Datacenter

Memory per GPU

3.6x more on B300

B300

288 GB HBM3e

H100

80 GB HBM3 94 GB on NVL

Memory bandwidth

2.4x higher on B300

B300

8,000 GB/s

H100

3,350 GB/s 2,000 GB/s on PCIe 3,900 GB/s on NVL

GPU interconnect

2x higher on B300

B300

NVLink 1,800 GB/s

H100

NVLink 900 GB/s No NVLink on PCIe NVLink 600 GB/s on NVL

Precision support

B300

FP4 FP6 FP8 FP16 BF16 TF32 FP32 FP64 INT8

H100

FP8 FP16 BF16 TF32 FP32 FP64 INT8

Highlighted formats are supported by only one of the two.

Architecture

B300

Blackwell Ultra

H100

Hopper

Released

2 years newer on B300

B300

Q1 2025

H100

Q3 2022

Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.

Source: B300 datasheet and H100 datasheet.

Price comparison

Cheapest on-demand

4x higher on B300

B300

$6.90 / GPU / hr

H100

$1.73 / GPU / hr

Typical rate

2.3x higher on B300

B300

$7.85 / GPU / hr

H100

$3.39 / GPU / hr

Median across providers, one vote each, so a large catalog does not outweigh a small one.

Spot floor

15x higher on B300

B300

$4.30 / GPU / hr

H100

$0.29 / GPU / hr

Full price range

B300

$4.15 - $17.80 / GPU / hr

H100

$0.29 - $14.90 / GPU / hr

Lowest to highest listing per GPU-hour, across on-demand, spot, reserved and custom.

Providers listing it

26 more on H100

B300

H100

Price, last 90 days

B300

−1%

H100

+12%

Change in the market-wide median, which moves when providers reprice and when cheaper or more expensive listings enter the market.

Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.

Offers and availability

How this list works

Order

Each provider appears once per GPU. We pick the one configuration that speaks for that provider, and rank on it in this order:

Availability: in stock, then waitlist, then not reported, then out of stock. A price you can act on outranks a cheaper one you cannot.
Billing type: on-demand first, then reserved, then spot, then quote-only. On-demand leads because it is the only rate you can hold without committing to anything.
Price: the lowest per-GPU hourly rate the provider lists, converted to USD.

The configuration we pick is chosen the same way, availability before billing before price. The rest of that provider's configurations are on the GPU's own page.

Ties sort alphabetically. Reserved rates are not separated by term length, so a three-year commitment can sit above a one-month one: the label beneath each price says which you are looking at. Providers who publish no rate are listed last within their group.

Transparency and funding

Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.