RTX 4090 GPU Rental Prices & Live Availability
As of , the cheapest single RTX 4090 confirmed in stock is $0.26 per GPU-hour on Theta EdgeCloud. The lowest listed price is $0.20 per GPU-hour on Vast, but that configuration is currently reported out of capacity. GPU Finder compares 6 providers for this size and refreshes availability hourly. Methodology.
Structured offer basis: 75 current 1× RTX 4090 listings range from $0.20 to $3.39 USD per physical GPU-hour. Whole-node prices for other GPU counts are not mixed into this range.
Cheapest single RTX 4090 rental
verifiedCheapest RTX 4090 confirmed in stock right now
Limited- Is now a good time to rent an RTX 4090 cloud GPU?
- ■ mid-range vs the last 6 months — The 1× RTX 4090 on-demand floor is $0.14/hr ($0.14/GPU-hr), up 24% vs last month — 6-month range $0.11–$0.60/hr for 1× nodes. In short, prices are mid-range versus the last 6 months.
- What is the cheapest RTX 4090 cloud GPU available right now?
- Cheapest RTX 4090 confirmed in stock right now: $0.26/GPU-hr on Theta EdgeCloud (1× listing, $0.26/hr).
Prices are the cheapest listed on-demand rates; “in stock” means the provider reported capacity on our last hourly check. How we compute this →
RTX 4090 rental prices by provider
- community-rtx-4090-x1Limited0% · 30d$0.26/hr1× RTX 409032 vCPU16 GBtheta-community
Get notified when RTX 4090 drops in price or reliability changes
One email per change, max once a day. We send a confirmation link first; one-click unsubscribe in every email.
RTX 4090 (1× GPU) availability — last 7 days
No provider held 1× RTX 4090 ≥80% available across all 7 days. Polled hourly · 7 providers tracked · 7-day window.
| Provider | Tue29 | Wed30 | Thu1 | Fri2 | Sat3 | Sun4 | Mon5 | Week |
|---|---|---|---|---|---|---|---|---|
| Shadeform | 48% | |||||||
| Runpod | 26% | |||||||
| Lium | 8% | |||||||
| Vast | 0% | |||||||
| AceCloud | 0% | |||||||
| Packet | 0% | |||||||
| Theta EdgeCloud | 0% |
30-day reliability depth
GPU Finder does not treat availability as a static yes/no flag. For RTX 4090, current stock badges are paired with a 30-day reliability score based on our hourly stock checks — the share of tracked time each listing was reported available. How we compute this →
- 223
- listings with a 30-day score
- 100%
- of listings on this page have a score
- 30d
- longest stock history on this page
Strongest reliability signals here: Shadeform (57%, 30d covered), Packet (55%, 30d covered), Lium (49%, 30d covered).
Caveat: scores stay hidden until a listing has at least 48 tracked hours, and some provider APIs expose coarse capacity levels instead of exact stock counts. Use the score as historical depth beside current availability, not as a guarantee that a GPU will still be allocatable when you click through.
Price History & Comparison
Full RTX 4090 price history (7 months) →Spot pricing decision guide
Treat spot as a risk-adjusted capacity decision, not just a cheaper number.
per GPU-hour
10% below on-demand floor
daily median for the same offers with complete history
median hidden until ≥3 rows across ≥2 providers
Cheapest trusted interruptible capacity is on Vast; 1 provider currently report spot or interruptible stock (83 units/signals visible).
Vast has kept spot or interruptible capacity in stock most reliably over the last 30 days (9%). See the availability section for the broader stock history.
There is a valid spot or interruptible row, but not enough trusted history to overstate the signal.
Good fit: checkpointed batch jobs, flexible training, and experiments that can restart. Avoid for production serving, deadline-bound runs, or jobs that cannot tolerate eviction.
Source caveat: Runpod exposes explicit spot fields; Vast is labeled interruptible/bid-floor. Lambda is treated as on-demand-only unless a verified spot field is added.
About the RTX 4090
The NVIDIA RTX 4090 is a consumer GPU that has become the de facto choice for individual researchers, small teams, and cost-sensitive inference. Its 24 GB of GDDR6X and Ada Lovelace Tensor Cores deliver performance rivaling datacenter GPUs at a fraction of the cost. The trade-off: no ECC, no NVLink, and a 24 GB VRAM ceiling. But for workloads that fit, nothing else comes close on cost-per-FLOP.
Key Specifications
| Architecture | Ada Lovelace (AD102) |
| GPU Memory | 24 GB GDDR6X |
| Memory Bandwidth | 1,008 GB/s |
| FP16 Tensor Core | 330 TFLOPS |
| TDP | 450W |
| Interconnect | PCIe Gen4 x16 |
| Release Year | 2022 |
Cloud Pricing Context
The RTX 4090 is the cheapest high-performance GPU in the cloud, starting around $0.18/hr on marketplace providers. It is offered almost exclusively by neocloud and bare-metal providers. For any workload fitting in 24 GB, it consistently delivers the best performance per dollar.
Best For
- Fine-tuning 7B-parameter models with LoRA/QLoRA adapters
- Local-quality inference for Llama, Mistral, and similar models
- Rapid prototyping where cost matters more than ECC
- Stable Diffusion, ComfyUI, and image generation workloads