Most deployedCloud GPU
NVIDIA

A100

A100 is available through OneInfer GPU marketplace with live provider pricing, regions, VRAM, and deployment options from the API.

VRAM
80GB
Best price
$0.99/gpu/hr
Providers
4 available
Regions
6 regions
VRAM
80GB
CUDA cores
6,912
TDP
400W
Bandwidth
N/A
Process node
7nm
Launch date
N/A

Available from 4 providers

Sorted by price · click price to re-sort
ProviderRegionsConfigPrice / hr ▾Availability
vastaivastai
AS-JP-01, AS-AE-011x 80GB$0.99Limited
runpodrunpod
US-WA-01, US-KS-02, US-MD-011x 80GB$1.59Limited
vastaivastai
US-CA-014x 80GB$3.69In stock
vastaivastai
AS-JP-014x 80GB$4.59In stock

Full specifications

Data from GPU specs and provider APIs
AI TOPS624
FP8 TFLOPS624
FP16 TFLOPS311.84
BF16 TFLOPS311.84
FP32 TFLOPS19.49
INT8 TOPS624
Sparse multiplier2

Benchmarks

A100 vs comparable GPUs on the platform

Inference throughput

7B model · tokens/sec

B200 SXM15,000
H200 SXM8,500
H100620
A100500
GeForce RTX 5090180

Training performance

Overall training multiplier

B200 SXM30x
H200 SXM18x
H10015x
A1003.4x
L40S2.8x

GeekBench OpenCL

Compute benchmark score

GeForce RTX 5090367,740
H200 SXM343,598
L40S337,706
H100336,474
B200 SXM333,768

Best for

LLM fine-tuningHigh-throughput inferenceMulti-modal model trainingLarge-batch distributed trainingRAG pipelines at scale

Similar GPUs

H100
80GB
$1.74/gpu/hr
View details →
RTX 6000 Ada Generation
48GB
$0.53/gpu/hr
View details →
L40S
48GB
$0.55/gpu/hr
View details →
A40
48GB
$0.07/gpu/hr
View details →

Ready to deploy A100?

Spin up an instance in minutes from your choice of 4 providers.