The B300 is newer, with 3.6x the memory and 4.1x the bandwidth. The A100 is typically cheaper.
At a glance
Memory
3.6x more on B300
- A100
- 80 GB
- B300
- 288 GB
Memory bandwidth
4.1x higher on B300
- A100
- 1.94 TB/s
- B300
- 8.00 TB/s
Cheapest on-demand
92% cheaper on A100
- A100
- $0.40 /GPU/hr
- B300
- $4.99 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | A100 | B300 | Difference |
|---|---|---|---|
| On-demand | $1.79 /GPU/hr from $0.40 | $7.89 /GPU/hr from $4.99 | 77% cheaper on A100 |
| Reserved | $1.60 /GPU/hr from $0.30 (3 mo) | $6.25 /GPU/hr from $4.25 | 74% cheaper on A100 |
| Spot | $0.99 /GPU/hr from $0.17 | $5.55 /GPU/hr from $4.08 | 82% cheaper on A100 |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. Verify before provisioning. More on how we price.
Price history
A100 vs B300 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A100 | B300 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 80 GB HBM2e 40 GB on SXM, PCIe | 288 GB HBM3e | 3.6x more on B300 |
| Bandwidth | 1,935 GB/s 2,039 GB/s on SXM 1,555 GB/s on SXM, PCIe | 8,000 GB/s | 4.1x higher on B300 |
| Bus width | 5,120-bit | 8,192-bit | 60% wider on B300 |
| Compute · dense | |||
| FP4 | Not supported | 14,000 TFLOPS | B300 only |
| FP8 | Not supported | 4,500 TFLOPS | B300 only |
| FP16 / BF16 | 312 TFLOPS | 2,250 TFLOPS | 7.2x higher on B300 |
| INT8 | 624 TOPS | 153.5 TOPS | 4.1x higher on A100 |
| FP32 | 19.5 TFLOPS | 75 TFLOPS | 3.8x higher on B300 |
| FP64 | 9.7 TFLOPS | 1.2 TFLOPS | 8.1x higher on A100 |
| Platform | |||
| Interconnect | NVLink 600 GB/s | NVLink 1,800 GB/s | 3x higher on B300 |
| Board power | 300 W | 1,100 W | 3.7x higher on B300 |
| Released | Q2 2020 | Q1 2025 | 5 years newer on B300 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32FP64INT4INT8 | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A100 datasheet and B300 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | A100 | B300 |
|---|---|---|
Vast.ai
USA
|
$0.40 /GPU/hr On-demand SXM | $9.94 /GPU/hr On-demand |
GPU.ai
UAE
|
$0.47 /GPU/hr On-demand | $7.89 /GPU/hr On-demand SXM |
Runpod
USA
|
$1.39 /GPU/hr On-demand SXM | $7.89 /GPU/hr On-demand SXM |
Lium
Distributed
|
$0.98 /GPU/hr On-demand SXM | $8.50 /GPU/hr On-demand SXM |
Jarvislabs
India
|
$0.89 /GPU/hr On-demand | -- |
Thunder Compute
USA
|
$1.09 /GPU/hr On-demand | -- |
Hyperstack
UK
|
$1.35 /GPU/hr On-demand PCIe | -- |
Massed Compute
USA
|
$1.38 /GPU/hr On-demand SXM | -- |
Daytona
USA
|
-- | $7.10 /GPU/hr On-demand |
EmpirioLabs AI
USA
|
-- | $17.00 /GPU/hr On-demand |
Verda
Finland
|
-- | $4.40 /GPU/hr Spot SXM |
Spheron
Singapore
|
-- | $5.81 /GPU/hr Spot SXM |
48 providers list the A100 and 34 the B300. Every listing is on the A100 page and the B300 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia H100
80 GB HBM3 · 73% more bandwidth than the A100
From $1.30 /GPU/hr Compare -
Nvidia RTX 5090
32 GB GDDR7 · PCIe only
From $0.35 /GPU/hr Compare
-
Nvidia RTX 4090
24 GB GDDR6X · 48% less bandwidth than the A100
From $0.26 /GPU/hr Compare
-
Nvidia B200
180 GB HBM3e · released Q1 2024
From $3.75 /GPU/hr Compare
Our data for Nvidia A100 was last updated on Sept. 14, 2026, and for Nvidia B300 on Sept. 14, 2026.