RTX 4090 rental prices: cheapest $/hr today
The cheapest on-demand RTX 4090 rental today is $0.35/hr on TensorDock, updated 2026-10-11. 24 GB VRAM, NVIDIA.
Salad prices use its Lowest priority tier: workloads can be interrupted. These rates suit retryable batch jobs; they do not guarantee availability or uninterrupted runtime. Compare Salad priority tiers.
Community cloud from $0.16 (SaladCloud), can be interrupted
Marketplace hosts from $0.35 (Lium, Hong Kong, Hong Kong), one independent owner's server
Pricing at a glance
All current RTX 4090 offers
More filters: provider, memory, node size, stock, sort, price unit
| GPU / provider | Billing | $/GPU-hour | Node · total per hour | Rent |
|---|---|---|---|---|
| RTX 4090 · TensorDock24 GB | on-demand | $0.35 | – | Rent → |
| RTX 4090 · Spheron24 GB | on-demand | $0.48−18.6% in 30 days | – | Rent → |
| RTX 4090 · RunPod24 GB | secure cloud | $0.89+20.3% in 30 days | – | Rent → |
| RTX 4090 · Daytona24 GB · RTX 4090; GPU rate only, CPU/memory/disk billed separately | on-demand | $0.99 | – | Rent → |
| RTX 4090 · SaladCloud24 GB | community cloud | $0.16 | – | Rent → |
| RTX 4090 · RunPod24 GB | community cloud | $0.34 | – | Rent → |
| RTX 4090 · Lium24 GB · 8-GPU host | marketplace host | $0.35 | 8× $2.80 | In stockRent →2026-10-11Details
|
| RTX 4090 · Lium24 GB · 1-GPU host | marketplace host | $0.42 | 1× $0.42 | In stockRent →2026-10-11Details
|
| RTX 4090 · Lium24 GB · ×3 hosts | marketplace host | $0.45 | 1× $0.45 | In stockRent →2026-10-11Details
|
| RTX 4090 · Lium24 GB · 1-GPU host | marketplace host | $0.48 | 1× $0.48 | In stockRent →2026-10-11Details
|
| RTX 4090 · Lium24 GB · 1-GPU host | marketplace host | $0.50 | 1× $0.50 | In stockRent →2026-10-11Details
|
| RTX 4090 · Lium22 GB · ×2 hosts | marketplace host | $0.55 | 1× $0.55 | In stockRent →2026-10-11Details
|
| RTX 4090 · Daytona24 GB · RTX 4090; GPU rate only, CPU/memory/disk billed separately | spot / interruptible | $0.57 | – | Rent → |
| RTX 4090 · Lium24 GB · ×2 hosts | marketplace host | $0.58 | 1× $0.58 | In stockRent →2026-10-11Details
|
| RTX 4090 · RunPod24 GB · Flex worker | serverless | $1.10$0.000306/sec | – | Rent → |
Try another provider or reduce the minimum memory.
Tables rank by price, lowest first. Commercial relationships never affect ordering. How we collect and rank prices.
Same GPU, provider, billing and price on several hosts or listings: one row, with the count. – means the provider does not state it.
Monthly view assumes 730 hours of continuous use. Daily view assumes 24 hours.
On-demand and secure-cloud rates are capacity the provider runs, with no reservation. Spot and community capacity can be interrupted. A marketplace host is one independent owner's server listed on a marketplace. Prices are per GPU per hour, before storage and data transfer. Every row shows the date it was checked.
RTX 4090 hardware specs
| Architecture | Ada Lovelace |
|---|---|
| VRAM | 24 GB |
| FP16 TFLOPS (dense) | 165 |
| Memory bandwidth | 1008 GB/s |
| TDP | 450 W |
| Interconnect | PCIe Gen4 |
| Launched | 2022 |
Datasheet spec for the RTX 4090 variant. Source: www.nvidia.com.
Compare RTX 4090 configurations
RTX 4090 purchase prices · Rent or buy calculator · Compare two GPUs
- SaladCloud RTX 4090 pricing
- RunPod RTX 4090 pricing
- Lium RTX 4090 pricing
- TensorDock RTX 4090 pricing
- Spheron RTX 4090 pricing
- Daytona RTX 4090 pricing
LLM memory estimates for this GPU
These models have an estimated inference footprint within 24 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.
| Model | 16-bit GB | 8-bit GB | 4-bit GB |
|---|---|---|---|
| Qwen2.5 32B | 79.9 | 40.6 | 20.9 ✓ |
| Qwen2.5 Coder 32B | 79.9 | 40.6 | 20.9 ✓ |
| DeepSeek R1 Distill Qwen 32B | 79.9 | 40.6 | 20.9 ✓ |
| Qwen3 32B | 79.9 | 40.6 | 20.9 ✓ |
| Qwen3 30B A3B | 73.8 | 37.1 | 18.8 ✓ |
| Mistral Small 24B 2501 | 57.4 | 29.1 | 14.9 ✓ |
| Qwen2.5 14B | 36.4 | 18.7 ✓ | 9.8 ✓ |
| Qwen2.5 Coder 14B | 36.4 | 18.7 ✓ | 9.8 ✓ |
| DeepSeek R1 Distill Qwen 14B | 36.4 | 18.7 ✓ | 9.8 ✓ |
| Qwen3 14B | 36.2 | 18.5 ✓ | 9.7 ✓ |
| phi 4 | 36.2 | 18.6 ✓ | 9.8 ✓ |
| Mistral Nemo 2407 | 30.2 | 15.5 ✓ | 8.2 ✓ |
| Qwen3 8B | 20.4 ✓ | 10.6 ✓ | 5.6 ✓ |
| DeepSeek R1 Distill Llama 8B | 19.9 ✓ | 10.3 ✓ | 5.5 ✓ |
| Qwen2.5 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| Qwen2.5 Coder 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| DeepSeek R1 Distill Qwen 7B | 18.6 ✓ | 9.4 ✓ | 4.9 ✓ |
| Mistral 7B v0.3 | 18.0 ✓ | 9.3 ✓ | 5.0 ✓ |
| Qwen3 4B | 10.4 ✓ | 5.6 ✓ | 3.1 ✓ |
| Qwen2.5 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen2.5 Coder 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen3 1.7B | 5.4 ✓ | 3.0 ✓ | 1.8 ✓ |
| DeepSeek R1 Distill Qwen 1.5B | 4.4 ✓ | 2.3 ✓ | 1.2 ✓ |
| Qwen2.5 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen2.5 Coder 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen3 0.6B | 2.4 ✓ | 1.5 ✓ | 1.0 ✓ |
| Qwen2.5 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
| Qwen2.5 Coder 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
Compare model memory requirements or change context and memory assumptions on a model's page.
When to choose RTX 4090
Use the model memory estimates above to check whether your weights, context and batch size fit within 24 GB. Then compare the exact variant, node size and software support. Capacity alone does not establish inference speed or training throughput.
If your workload fits within 16 GB, compare RTX A4000 rental prices from $0.10/GPU-hour. The smaller memory budget is the trade-off; price alone does not make the cards interchangeable.
RTX 4090 price changes
- 30 days: -0.7% across 3 matching firm-price configurations since 2026-09-11.
- 90 days: 8.1% across 2 matching firm-price configurations since 2026-07-13.
Changes use the geometric mean of price ratios for the same provider, variant, tier, GPU count, instance and region. New listings are not counted as price changes.
Price history
on-demand rate per day · median on-demand rate per day (dashed), since 2026-07-05: $0.35 low · $0.69 high. Full ledger on the history hub.
FAQ
The cheapest RTX 4090 rental we have is $0.35 per GPU-hour on TensorDock (on-demand), updated 2026-10-11.
24 GB.
TensorDock has the cheapest verified on-demand rate today at $0.35 per GPU-hour; interruptible spot/community capacity starts at $0.16. Verified 2026-10-11.
Related
All 24 GB+ GPUs · GPUs under $1/hr · Price movers this week · TensorDock review · RTX 4090 vs RTX 5090 · RTX 4090 vs A100 · RTX 3090 vs RTX 4090 · Cloud GPU for speech recognition · Cloud GPU for cloud gaming and game streaming · How much does an RTX 4090 cost to rent?
Should you rent or buy?
Compare RTX 4090 purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates.