GeForce RTX 4090

Every provider's rate, side by side.

GeForce RTX 4090 is available through the OneInfer GPU marketplace with live provider pricing, regions, VRAM, and deployment options from the API.

11 providers list it in 33 regions, from $0.35 per GPU-hour with vastai. It has 24 GB of GPU memory. Pick a provider and region, deploy it from the OneInfer Console with your own Docker image, connect over SSH, and pay from one pay-as-you-go wallet while it runs.

Deploy the GeForce RTX 4090 in 4 steps

Step 1 of 4

11 providers list the GeForce RTX 4090, from $0.35 per GPU-hour. The table below sorts them by price.

Cloud GPU
VRAM
24GB
CUDA cores
16,384
TDP
450W
Bandwidth
N/A
Process node
5nm
Launch date
N/A

Where you can run it

The GeForce RTX 4090 is available now in 33 of the 98 regions OneInfer has GPUs in. Pick a region to see who offers it there, or see every GPU by region.

Available nowNot available

Americas

Europe

Asia-Pacific

Prices are per GPU-hour, the lowest in each region. Grey regions have other GPUs, not the GeForce RTX 4090.

Available from 11 providers

Sorted by price. Select the price heading to re-sort.

GeForce RTX 4090 providers, regions, configurations and hourly prices
ProviderRegionsConfigAvailabilityDeploy
vastaivastai
EU-BG-01, CN-01, US-ID-01, US-IA-01, AS-JP-01, CN-JS-01, US-NY-01, EU-MK-01, EU-NO-01, CA-QC-01, EU-SE-01, AS-TW-01, EU-UA-01, US-WA-014x 24GB$0.35$1.39/hr for 4 GPUsAvailable
vastaivastai
US-CA-01, CN-01, EU-FR-01, EU-IT-01, CN-JS-01, US-MN-01, EU-MD-01, US-MT-01, US-NY-01, EU-NO-01, US-PA-01, CA-QC-01, EU-RO-01, AS-KR-01, EU-ES-01, US-TX-01, EU-NL-01, US-UT-011x 24GB$0.35Available
vastaivastai
US-CA-01, AS-JP-018x 24GB$0.36$2.89/hr for 8 GPUsAvailable
vastaivastai
US-CA-01, CN-01, AS-JP-01, EU-RO-01, AS-KR-01, US-TX-01, EU-GB-01, US-VA-01, CN-ZJ-011x 24GB$0.38Available
vastaivastai
EU-BG-01, US-CA-01, EU-FI-01, US-IA-01, AS-JP-01, EU-MK-01, EU-NO-01, CA-QC-01, EU-ES-01, EU-SE-01, EU-NL-01, EU-GB-01, US-UT-012x 24GB$0.40$0.81/hr for 2 GPUsAvailable
vastaivastai
US-CA-01, AS-JP-014x 24GB$0.45$1.82/hr for 4 GPUsAvailable
vastaivastai
US-CA-01, AS-JP-01, US-TX-012x 24GB$0.45$0.91/hr for 2 GPUsAvailable
vastaivastai
AS-TW-01, US-UT-01, US-WA-018x 24GB$0.47$3.73/hr for 8 GPUsAvailable
runpodrunpod
EU-RO-01, EU-IS-02, US-IL-011x 24GB$0.89Available
runpodrunpod
EU-RO-01, EU-IS-02, US-IL-012x 24GB$0.89$1.78/hr for 2 GPUsAvailable
runpodrunpod
EU-IS-02, US-IL-014x 24GB$0.89$3.56/hr for 4 GPUsAvailable

Full specifications

Data from GPU specs and provider APIs

AI TOPS
1,321
FP8 TFLOPS
1,321
FP16 TFLOPS
82.58
BF16 TFLOPS
82.58
FP32 TFLOPS
82.58
INT8 TOPS
1,321
Sparse multiplier
2

Benchmarks

GeForce RTX 4090 vs comparable GPUs on the platform

Inference throughput

7B model, tokens per second

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

Ready to deploy GeForce RTX 4090?

Deploy from your choice of 11 providers.