RTX PRO 6000 Cloud Rental Pricing
Blackwell workstation/server GPU with 96GB GDDR7, popular for single-GPU inference of large open models.
17 offers from 15 providers · updated November 22, 2026
| Provider | Variant | VRAM | On-demand /hr | Spot /hr | Per month | Billing |
|---|---|---|---|---|---|---|
| Vast.ai | RTX PRO 6000 Max-Q | 96GB | $0.80 | — | $584 | per second |
| Vast.ai | RTX PRO 6000 (Workstation) | 96GB | $1.00 | — | $730 | per second |
| Vast.ai | RTX PRO 6000 (Server) | 96GB | $1.07 | — | $781 | per second |
| Nebius AI Cloud | RTX PRO 6000 | 96GB | $1.80 | $0.79 | $1,314 | per second |
| Hyperstack | RTX PRO 6000 SE | 96GB | $1.85 | $1.48 | $1,351 | per minute |
| Jarvislabs | RTX PRO 6000 | 96GB | $2.19 | $1.15 | $1,599 | per minute |
| Runcrate | RTX PRO 6000 | 96GB | $2.41 | — | $1,759 | per second |
| CoreWeave | RTX PRO 6000 (min 8) | 96GB | $2.50 | $1.39 | $1,825 | per hour |
| Fluence | RTX PRO 6000 | 96GB | $2.58 | — | $1,885 | per hour |
| RunPod credits | RTX PRO 6000 | 96GB | $2.69 | — | $1,964 | per ms |
| Verda | RTX PRO 6000 | 96GB | $2.84 | $1.42 | $2,070 | per hour |
| Latitude.sh | RTX PRO 6000 SE (min 8) | 96GB | $3.00 | — | $2,190 | per hour |
| Modal credits | RTX PRO 6000 | 96GB | $3.03 | — | $2,212 | per second |
| AWS credits | RTX PRO 6000 | 96GB | $3.36 | $2.54 | $2,455 | per second |
| Google Cloud | RTX PRO 6000 | 96GB | $4.50 | $1.81 | $3,285 | per second |
| Oracle Cloud | RTX PRO 6000 (min 8) | 96GB | $4.50 | — | $3,285 | per second |
| Microsoft Azure | RTX PRO 6000 | 96GB | $5.50 | $1.02 | $4,015 | per second |
Per GPU-hour, on-demand unless noted. Monthly = 730 hours. Check each provider for region availability and multi-GPU node minimums.
Or run models at home
If you rent a RTX PRO 6000 mainly for inference, a mini PC with lots of unified memory can hold the same open models on your desk. It's slower per token than a RTX PRO 6000, but there's no hourly bill.Compare mini PCs for local LLMs.
GMKtec EVO-X5 Pro
- Chip
- AMD Ryzen AI Max+ PRO 495
- Memory
- 192GB unified (up to 160GB as VRAM)
- Bandwidth
- 273 GB/s
- Runs
- Qwen3 235B-A22B, MiniMax M2.1, plus everything the 128GB boxes run
AMD's 2026 chip. 192GB / 2TB; 4TB is $7,099.
NVIDIA DGX Spark
- Chip
- NVIDIA GB10 Grace Blackwell
- Memory
- 128GB unified
- Bandwidth
- 273 GB/s
- Runs
- gpt-oss-120b, Qwen3.5 122B-A10B, Llama 4 Scout; CUDA, so most training tools work
128GB / 4TB Founders Edition. Partner GB10 boxes from ASUS, MSI and Dell cost $5,599 to $8,500.
Mac Studio (M5 Max)
- Chip
- Apple M5 Max
- Memory
- 48GB or 128GB unified
- Bandwidth
- 614 GB/s (40-core GPU)
- Runs
- 128GB: gpt-oss-120b, Qwen3.5 122B-A10B, at more than twice the bandwidth of the AMD boxes
128GB is $5,099. The M5 Ultra (96GB to 512GB, 1.2 TB/s) starts at $5,499.
GMKtec EVO-X2
- Chip
- AMD Ryzen AI Max+ 395
- Memory
- 64GB or 128GB unified (up to 96GB as VRAM)
- Bandwidth
- 256 GB/s
- Runs
- 128GB: gpt-oss-120b, Qwen3.5 122B-A10B, GLM-4.5 Air. 64GB: 30B-class models
128GB / 1TB is $3,499.99. The cheapest 128GB Ryzen AI Max box we found.
Starting prices from each maker's own store on November 22, 2026; they change often, so check the store. "Runs" is a rough guide for 4-bit quantized models.
RTX PRO 6000 rental FAQ
How much does it cost to rent an RTX PRO 6000?
On-demand RTX PRO 6000 rental ranges from $0.80 to $5.50 per GPU-hour across 15 providers (median $2.58), as of November 22, 2026. Spot/interruptible capacity starts at $0.79/hr.
What is the cheapest RTX PRO 6000 cloud provider?
Vast.ai has the lowest on-demand RTX PRO 6000 price we track at $0.80 per GPU-hour (RTX PRO 6000 Max-Q).
How much does an 8x RTX PRO 6000 server cost per month?
At the cheapest on-demand rate ($0.80/GPU-hour), 8x RTX PRO 6000 running 24/7 costs about $4,672 per month (730 hours). At the median rate it is about $15,082.