The RTX PRO 6000 has 3x the memory, while the RTX 5090 has 12% more bandwidth. The RTX 5090 is typically cheaper.
At a glance
Memory
3x more on RTX PRO 6000
- RTX 5090
- 32 GB
- RTX PRO 6000
- 96 GB
Memory bandwidth
12% higher on RTX 5090
- RTX 5090
- 1.79 TB/s
- RTX PRO 6000
- 1.60 TB/s
Cheapest on-demand
46% cheaper on RTX 5090
- RTX 5090
- $0.35 /GPU/hr
- RTX PRO 6000
- $0.65 /GPU/hr
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX 5090 | RTX PRO 6000 | Difference |
|---|---|---|---|
| On-demand | $0.64 /GPU/hr from $0.35 | $2.19 /GPU/hr from $0.65 | 71% cheaper on RTX 5090 |
| Reserved | $0.61 /GPU/hr from $0.21 (1 mo) | $1.81 /GPU/hr from $0.48 (1 mo) | 66% cheaper on RTX 5090 |
| Spot | $0.47 /GPU/hr from $0.25 | $1.29 /GPU/hr from $0.26 | 64% cheaper on RTX 5090 |
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
RTX 5090 vs RTX PRO 6000 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 5090 | RTX PRO 6000 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 32 GB GDDR7 | 96 GB GDDR7 | 3x more on RTX PRO 6000 |
| Bandwidth | 1,792 GB/s | 1,597 GB/s | 12% higher on RTX 5090 |
| Bus width | 512-bit | 512-bit | Identical |
| Compute · dense | |||
| FP4 | 1,676 TFLOPS | 2,000 TFLOPS | 19% higher on RTX PRO 6000 |
| FP8 | 419 TFLOPS | 1,000 TFLOPS | 2.4x higher on RTX PRO 6000 |
| FP16 / BF16 | 209.5 TFLOPS | 500 TFLOPS | 2.4x higher on RTX PRO 6000 |
| INT8 | 838 TOPS | 1,000 TOPS | 19% higher on RTX PRO 6000 |
| FP32 | 104.8 TFLOPS | 120 TFLOPS | 15% higher on RTX PRO 6000 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 575 W | 600 W | Within 5% |
| Released | Q1 2025 | Q1 2025 | |
| Precision | |||
| Supported formats | FP4FP8FP16BF16TF32FP32INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 5090 datasheet and RTX PRO 6000 datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. Providers that rent both are listed first.
| Provider | RTX 5090 | RTX PRO 6000 |
|---|---|---|
HyperAI
Hong Kong
|
$0.35 /GPU/hr On-demand | $0.80 /GPU/hr On-demand |
Vast.ai
USA
|
$0.44 /GPU/hr On-demand | $1.02 /GPU/hr On-demand |
GPUhub
Singapore
|
$0.46 /GPU/hr On-demand | $1.10 /GPU/hr On-demand |
Lium
Distributed
|
$0.65 /GPU/hr On-demand | $1.29 /GPU/hr On-demand |
GPU.ai
UAE
|
$0.47 /GPU/hr On-demand | -- |
Salad
Distributed
|
$0.50 /GPU/hr On-demand | -- |
Theta EdgeCloud
Distributed
|
$0.64 /GPU/hr On-demand | -- |
Nova Cloud
Canada
|
$0.66 /GPU/hr On-demand PCIe | -- |
Packet·ai
USA
|
-- | $0.66 /GPU/hr On-demand |
Runpod
USA
|
-- | $1.64 /GPU/hr On-demand |
UpCloud
Finland
|
-- | $1.88 /GPU/hr On-demand |
EcoHash
USA
|
-- | $1.89 /GPU/hr On-demand PCIe |
22 providers list the RTX 5090 and 52 the RTX PRO 6000. Every listing is on the RTX 5090 page and the RTX PRO 6000 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia RTX 4090
24 GB GDDR6X · 44% less bandwidth than the RTX 5090
From $0.33 /GPU/hr Compare -
Nvidia L40S
48 GB GDDR6 · 52% less bandwidth than the RTX 5090
From $0.38 /GPU/hr Compare
-
Nvidia H100
80 GB HBM3 · 2.1x the bandwidth of the RTX PRO 6000
From $1.30 /GPU/hr Compare
-
Nvidia B200
180 GB HBM3e · 4.8x the bandwidth of the RTX PRO 6000
From $3.75 /GPU/hr Compare
-
Nvidia H200
141 GB HBM3e · 3x the bandwidth of the RTX PRO 6000
From $2.09 /GPU/hr Compare
Our data for Nvidia RTX 5090 was last updated on Sept. 14, 2026, and for Nvidia RTX PRO 6000 on Sept. 14, 2026.