GeForce RTX 5090

Every provider's rate, side by side.

GeForce RTX 5090 is available through the OneInfer GPU marketplace with live provider pricing, regions, VRAM, and deployment options from the API.

5 providers list it in 33 regions, from $0.46 per GPU-hour with vastai. It has 32 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 5090 in 4 steps

Step 1 of 4

5 providers list the GeForce RTX 5090, from $0.46 per GPU-hour. The table below sorts them by price.

Cloud GPU
VRAM
32GB
CUDA cores
21,760
TDP
575W
Bandwidth
N/A
Process node
5nm
Launch date
N/A

Where you can run it

The GeForce RTX 5090 is available now in 33 of the 96 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 5090.

Available from 5 providers

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

GeForce RTX 5090 providers, regions, configurations and hourly prices
ProviderRegionsConfigAvailabilityDeploy
vastaivastai
CA-AB-01, CN-AH-01, CN-BJ-01, EU-BG-01, US-CA-01, CN-01, EU-CZ-01, EU-FR-01, EU-DE-01, NA-MX-01, US-NC-01, CA-ON-01, US-PA-01, CA-QC-01, AS-KR-01, EU-SE-01, AS-TW-01, EU-GB-011x 32GB$0.46Available
vastaivastai
CA-AB-01, EU-CZ-01, US-NY-01, EU-NO-01, CA-ON-01, AS-TW-01, EU-GB-01, US-018x 32GB$0.47$3.74/hr for 8 GPUsAvailable
vastaivastai
CA-AB-01, CA-BC-01, CN-01, EU-CZ-01, EU-DE-01, CN-HN-01, US-NC-01, EU-NO-01, US-OH-01, US-PA-01, EU-PL-01, AS-SG-02, AS-KR-01, EU-ES-01, AS-TW-01, US-TX-01, AS-TH-01, EU-NL-01, EU-GB-012x 32GB$0.53$1.07/hr for 2 GPUsAvailable
vastaivastai
CA-AB-01, CA-BC-01, EU-BG-01, CN-01, EU-CZ-01, AS-JP-01, US-NJ-01, CA-ON-01, AS-KR-01, EU-ES-01, AS-TW-01, US-TX-01, EU-GB-014x 32GB$0.57$2.27/hr for 4 GPUsAvailable
runpodrunpod
EU-RO-011x 32GB$1.39Available

Full specifications

Data from GPU specs and provider APIs

AI TOPS
3,352
FP8 TFLOPS
415
FP16 TFLOPS
209.5
BF16 TFLOPS
209.5
FP32 TFLOPS
104.8
INT8 TOPS
2,792
Sparse multiplier
2

Benchmarks

GeForce RTX 5090 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 5090?

Deploy from your choice of 5 providers.