NVIDIA RTX A5000 (24GB GDDR6)
- 24GB GDDR6
- Memory
- 768GB/s
- Memory bandwidth
- Q2 2021
- Released
Price history
What it costs to rent an NVIDIA RTX A5000
The NVIDIA RTX A5000 is an Ampere-architecture inference NVIDIA GPU with 24GB of GDDR6 memory and 768 GB/s of memory bandwidth, released Q2 2021. It is built for inference, fine-tuning and mixed production workloads.
Renting one currently costs between $0.09 and $1.85 per GPU-hour across the 9 cloud providers we track, with a median of $0.26. The cheapest live rate is $0.09/hr from Salad (Spot), and hosting one pays about $0.20/hr on Nosana while it is running. All rates below are normalised to a single GPU per hour so providers with multi-GPU nodes compare like-for-like.
Where to rent the RTX A5000
How we rank
The median is one provider, one vote: each provider contributes the median of its own on-demand listings, then the headline is the median across providers — so no single marketplace or hyperscaler sets the price alone. Below two providers we show the range instead.
Default order is relevance, weighed the way a buyer would: price per GPU first, lightly blended with total node cost; on-demand preferred over spot and reserved when prices are close; established clouds edged above marketplaces; in-stock, recently-checked offers above stale ones; and no single provider is allowed to crowd the top. Click a column to sort by the raw numbers. No paid placements — ranking is never sold.
Scroll horizontally to compare all columns →
| Provider | Tier | Config | Total VRAM | Billing | Availability | Go to provider | ||
|---|---|---|---|---|---|---|---|---|
 SaladBest | GPU cloud | 1× RTX A5000 | 24GB | Spot | $0.09 | $0.09 | Rent | |
| Salad | GPU cloud | 1× RTX A5000 | 24GB | Community | $0.14 | $0.14 | Rent | |
 Nosana | GPU cloud | 1× RTX A5000 | 24GB | On-demand | $0.18 | $0.18 | Rent | |
 Vast.ai | GPU cloud | 5× RTX A5000 | 120GB | On-demand | $0.23 | $1.16 | Rent | |
 Hyperstack | GPU cloud | 1× RTX A5000 | 24GB | On-demand | $0.25 | $0.25 | Rent | |
 RunPod | GPU cloud | 1× RTX A5000 | 24GB | On-demand | $0.27 | $0.27 | Rent | |
| Nosana | GPU cloud | 1× RTX A5000 | 24GB | Community | $0.22 | $0.22 | Rent | |
| Salad | GPU cloud | 1× RTX A5000 | 24GB | Reserved | $0.20 | $0.20 | Rent | |
| Salad | GPU cloud | 1× RTX A5000 | 24GB | On-demand | $0.25 | $0.25 | Rent | |
| Vast.ai | GPU cloud | 8× RTX A5000 | 192GB | On-demand | $0.27 | $2.14 | Rent | |
 Massed Compute | GPU cloud | 1× RTX A5000 | 24GB | On-demand | $0.44 | $0.44 | Rent | |
| Massed Compute | GPU cloud | 2× RTX A5000 | 48GB | On-demand | $0.44 | $0.88 | Rent | |
| Massed Compute | GPU cloud | 4× RTX A5000 | 96GB | On-demand | $0.44 | $1.76 | Rent | |
| Massed Compute | GPU cloud | 8× RTX A5000 | 192GB | On-demand | $0.44 | $3.52 | Rent | |
| EExoscale | GPU cloud | 4× RTX A5000 | 96GB | On-demand | $1.14 | $4.56 | Rent | |
 Paperspace | Enterprise | 1× RTX A5000 | 24GB | On-demand | $1.38 | $1.38 | Rent | |
| EExoscale | GPU cloud | 2× RTX A5000 | 48GB | On-demand | $1.24 | $2.48 | Rent | |
| EExoscale | GPU cloud | 1× RTX A5000 | 24GB | On-demand | $1.34 | $1.34 | Rent | |
 Runcrate | Marketplace | from RTX A5000 | — | On-demand | $1.85 | — | Rent |
Earn by hosting the RTX A5000
How this is worked out
“Renters pay” is the median live rate for this GPU on that marketplace — the median, not the floor, because the cheapest listing is one host undercutting everyone. “You earn” is that figure less the platform’s cut.
“Per day” is a ceiling: 24 hours, every hour rented, which no host achieves — scale it by the utilisation you expect. A card sitting idle earns nothing.Fees marked as published come from the platform’s terms; the rest are our estimates, labelled on each row.
Technical specifications
| FP64 | 0.9 TFLOPS |
|---|---|
| FP32 | 28 TFLOPS |
- Memory
- 24 GB
- Memory bandwidth
- 768 GB/s
- TDP
- 230 W
- Process
- 8 nm
- Die size
- 628 mm²
- Transistors
- 28.3 B
- Foundry
- Samsung
- Released
- 12 Apr 2021
- Launch price
- $2,250
| Architecture | Ampere |
|---|---|
| CUDA cores | 8,192 |
| Memory | 24 GB GDDR6 ECC |
| Bandwidth | 768 GB/s |
| NVLink | two-card support |
| Power | 230 W |
- Class
- Inference
- Cloud providers
- 9 tracked
- Price range
- $0.09 – $1.85 / GPU / hr
Other inference cards
The Compute
NVIDIA A10SNAPSHOT 2026-10-12T06:41:40.609517+00:00 · BACK TO THE FULL INDEX