RTX 4090 rental price: from $0.35/hr today
The cheapest on-demand RTX 4090 today is $0.35 an hour at TensorDock, checked 22 October 2026; the typical provider charges $0.73.
- Community $0.16 SaladCloud, lowest priority SaladCloud, lowest priority, interruptible
- Serverless $1.10 RunPod, per second
- In stock $0.89 RunPod, stock reported
- Provider median $0.73
- Highest on-demand $0.99
- 8 offers
- 5 providers
- Cheapest unchanged since 18 July
- Same offers, 90 days: −1.0%
- Source tensordock.com
RTX 4090 offers: 8 configurations from 5 providers
More filters: provider, memory, node size, stock, place, sort, price unit
“Machines in” filters the 1 of 8 offers whose provider says where the machine is; the others are under “Place not stated”.
Daytona, SaladCloud and Spheron put GPUs in North America on their own pages, but none of their offers here says so.
Daytona and Spheron put GPUs in Europe on their own pages, but none of their offers here says so.
- Rent →
TensorDock1 configuration$0.35on-demandNot reportedOn-demand $0.35
Configuration Billing $/GPU-hour Node Stock · checked RTX 4090 on-demand $0.35 node size not published checked 22 October 2026 · source TensorDock RTX 4090 pricing · TensorDock: every GPU, fees and billing
- Rent →
Spheron1 configuration$0.58on-demandNot reportedOn-demand $0.58
Configuration Billing $/GPU-hour Node Stock · checked RTX 4090 on-demand $0.58 node size not published checked 22 October 2026 · source Spheron RTX 4090 pricing · Spheron: every GPU, fees and billing
- Rent →
RunPod1 configuration$0.89secure cloudIn stock: mediumOn-demand $0.89Spot & community $0.34Serverless $1.10
Configuration Billing $/GPU-hour Node Stock · checked RTX 4090 community cloud $0.34 node size not published checked 22 October 2026 · source RTX 4090 secure cloud $0.89 node size not published In stock: medium · checked 22 October 2026 · source RTX 4090Flex worker serverless $1.10 node size not published checked 22 October 2026 · source RunPod RTX 4090 pricing · RunPod: every GPU, fees and billing
- Rent →
Daytona1 configuration$0.99on-demandNot reportedOn-demand $0.99Spot & community $0.57
Configuration Billing $/GPU-hour Node Stock · checked RTX 4090RTX 4090; GPU rate only, CPU/memory/disk billed separately spot / interruptible $0.57 node size not published checked 22 October 2026 · source RTX 4090RTX 4090; GPU rate only, CPU/memory/disk billed separately on-demand $0.99 node size not published checked 22 October 2026 · source Daytona RTX 4090 pricing · Daytona: every GPU, fees and billing
- Rent →
SaladCloud1 configuration$0.16community cloudNot reportedlowest priority, interruptibleSpot & community $0.16
Configuration Billing $/GPU-hour Node Stock · checked RTX 4090 community cloud · lowest priority, interruptible $0.16 node size not published checked 22 October 2026 · source Salad's prices are its Lowest priority tier: a job can be interrupted, so they suit retryable batch work, with no promise of availability or uninterrupted runtime. Salad's priority tiers
SaladCloud RTX 4090 pricing · SaladCloud: every GPU, fees and billing
4 providers with on-demand offers, cheapest first. Tap a provider for its configurations.
| 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 | $0.58−19.4% in 30 days | – | Rent → |
| RTX 4090 · RunPod24 GB | secure cloud | $0.89+20.3% in 30 days | – | In stock: mediumRent →checked 22 OctDetails
|
| RTX 4090 · Daytona24 GB · RTX 4090; GPU rate only, CPU/memory/disk billed separately | on-demand | $0.99 | – | Rent → |
| RTX 4090 · SaladCloud24 GB | community cloudlowest priority, interruptible | $0.16 | – | Rent → |
| RTX 4090 · RunPod24 GB | community cloud | $0.34 | – | Rent → |
| RTX 4090 · Daytona24 GB · RTX 4090; GPU rate only, CPU/memory/disk billed separately | spot / interruptible | $0.57 | – | Rent → |
| 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.
Cite this data
GPU Rental Prices, "Rent 4090 GPU: RTX 4090 rental price: from $0.35/GPU-hour", prices checked 22 October 2026, https://gpurentalprices.com/rtx-4090
Quote it with a link to this page. Downloads of the whole dataset are on Data & API.
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 price history and range
- Cheapest on-demand$0.35(unchanged since 18 July)
- Provider median$0.73
- Cheapest spot$0.16
RTX 4090 price range by billing type
Per GPU-hour, today's offers. Axis $0 to $2.00.
CheapestProvider median (each provider's cheapest rate counted once; shown with three or more providers)
Price changes
- 30 days: −1.0% across 3 matching on-demand configurations since 22 September 2026.
- 90 days: −1.0% across 3 matching on-demand configurations since 24 July 2026.
Changes use the geometric mean of price ratios for the same provider, variant, tier, GPU count, instance and region (RunPod's place is where that day's stock sat, so it is not matched). New listings are not counted as price changes. Full ledger on the history hub.
RTX 4090 daily figures (110 days)
| Date | Cheapest on-demand | Provider median | Cheapest spot |
|---|---|---|---|
| 2026-10-22 | $0.35 | $0.73 | $0.16 |
| 2026-10-21 | $0.35 | $0.73 | $0.16 |
| 2026-10-20 | $0.35 | $0.69 | $0.16 |
| 2026-10-19 | $0.35 | $0.69 | $0.16 |
| 2026-10-18 | $0.35 | $0.74 | $0.16 |
| 2026-10-17 | $0.35 | $0.69 | $0.16 |
| 2026-10-16 | $0.35 | $0.73 | $0.16 |
| 2026-10-15 | $0.35 | $0.73 | $0.16 |
| 2026-10-14 | $0.35 | $0.73 | $0.16 |
| 2026-10-13 | $0.35 | $0.73 | $0.16 |
| 2026-10-12 | $0.35 | $0.69 | $0.16 |
| 2026-10-11 | $0.35 | $0.69 | $0.16 |
| 2026-10-10 | $0.35 | $0.73 | $0.16 |
| 2026-10-09 | $0.35 | $0.73 | $0.16 |
| 2026-10-08 | $0.35 | $0.66 | $0.16 |
| 2026-10-07 | $0.35 | $0.66 | $0.16 |
| 2026-10-06 | $0.35 | $0.66 | $0.16 |
| 2026-10-05 | $0.35 | $0.66 | $0.16 |
| 2026-10-04 | $0.35 | $0.58 | $0.16 |
| 2026-10-03 | $0.35 | $0.48 | $0.16 |
| 2026-10-02 | $0.35 | $0.48 | $0.16 |
| 2026-10-01 | $0.35 | $0.58 | $0.16 |
| 2026-09-30 | $0.35 | $0.74 | $0.16 |
| 2026-09-29 | $0.35 | $0.72 | $0.16 |
| 2026-09-28 | $0.35 | $0.48 | $0.16 |
| 2026-09-27 | $0.35 | $0.48 | $0.16 |
| 2026-09-26 | $0.35 | $0.48 | $0.16 |
| 2026-09-25 | $0.35 | $0.48 | $0.16 |
| 2026-09-24 | $0.35 | $0.48 | $0.16 |
| 2026-09-23 | $0.35 | $0.48 | $0.16 |
| 2026-09-22 | $0.35 | $0.72 | $0.16 |
| 2026-09-21 | $0.35 | $0.48 | $0.16 |
| 2026-09-20 | $0.35 | $0.58 | $0.16 |
| 2026-09-19 | $0.35 | $0.72 | $0.16 |
| 2026-09-18 | $0.35 | $0.59 | $0.16 |
| 2026-09-17 | $0.35 | $0.58 | $0.16 |
| 2026-09-16 | $0.35 | $0.72 | $0.16 |
| 2026-09-15 | $0.35 | $0.58 | $0.16 |
| 2026-09-14 | $0.35 | $0.48 | $0.16 |
| 2026-09-13 | $0.35 | $0.48 | $0.16 |
| 2026-09-12 | $0.35 | $0.72 | $0.16 |
| 2026-09-11 | $0.35 | $0.59 | $0.16 |
| 2026-09-10 | $0.35 | $0.72 | $0.34 |
| 2026-09-09 | $0.35 | $0.72 | $0.16 |
| 2026-09-08 | $0.35 | $0.72 | $0.16 |
| 2026-09-07 | $0.35 | $0.74 | $0.16 |
| 2026-09-06 | $0.35 | $0.74 | $0.16 |
| 2026-09-05 | $0.35 | $0.53 | $0.16 |
| 2026-09-04 | $0.35 | $0.53 | $0.16 |
| 2026-09-03 | $0.35 | $0.53 | $0.16 |
| 2026-09-02 | $0.35 | $0.53 | $0.16 |
| 2026-09-01 | $0.35 | $0.53 | $0.16 |
| 2026-08-31 | $0.35 | $0.53 | $0.16 |
| 2026-08-30 | $0.35 | $0.53 | $0.16 |
| 2026-08-29 | $0.35 | $0.53 | $0.16 |
| 2026-08-28 | $0.35 | $0.53 | $0.16 |
| 2026-08-27 | $0.35 | $0.53 | $0.16 |
| 2026-08-26 | $0.35 | $0.53 | $0.16 |
| 2026-08-25 | $0.35 | $0.53 | $0.16 |
| 2026-08-24 | $0.35 | $0.53 | $0.16 |
| 2026-08-23 | $0.35 | $0.53 | $0.16 |
| 2026-08-22 | $0.35 | $0.74 | $0.34 |
| 2026-08-21 | $0.35 | $0.53 | $0.20 |
| 2026-08-20 | $0.35 | $0.74 | $0.20 |
| 2026-08-19 | $0.35 | $0.53 | $0.20 |
| 2026-08-18 | $0.35 | $0.53 | $0.20 |
| 2026-08-17 | $0.35 | $0.53 | $0.20 |
| 2026-08-16 | $0.35 | $0.53 | $0.20 |
| 2026-08-15 | $0.35 | $0.53 | $0.20 |
| 2026-08-14 | $0.35 | $0.53 | $0.20 |
| 2026-08-13 | $0.35 | $0.53 | $0.20 |
| 2026-08-12 | $0.35 | $0.53 | $0.20 |
| 2026-08-11 | $0.35 | $0.53 | $0.20 |
| 2026-08-10 | $0.35 | $0.74 | $0.20 |
| 2026-08-09 | $0.35 | $0.74 | $0.20 |
| 2026-08-08 | $0.35 | $0.74 | $0.20 |
| 2026-08-07 | $0.35 | $0.74 | $0.20 |
| 2026-08-06 | $0.35 | $0.53 | $0.20 |
| 2026-08-05 | $0.35 | $0.53 | $0.20 |
| 2026-08-04 | $0.35 | $0.53 | $0.20 |
| 2026-08-03 | $0.35 | $0.53 | $0.20 |
| 2026-08-02 | $0.35 | $0.53 | $0.20 |
| 2026-08-01 | $0.35 | $0.53 | $0.20 |
| 2026-07-31 | $0.35 | $0.53 | $0.20 |
| 2026-07-30 | $0.35 | $0.53 | $0.20 |
| 2026-07-29 | $0.35 | $0.69 | $0.20 |
| 2026-07-28 | $0.35 | $0.53 | $0.20 |
| 2026-07-27 | $0.35 | $0.69 | $0.20 |
| 2026-07-26 | $0.35 | $0.69 | $0.20 |
| 2026-07-25 | $0.35 | $0.69 | $0.20 |
| 2026-07-24 | $0.35 | $0.69 | $0.20 |
| 2026-07-23 | $0.35 | $0.53 | $0.20 |
| 2026-07-22 | $0.35 | $0.58 | $0.20 |
| 2026-07-21 | $0.35 | $0.58 | $0.20 |
| 2026-07-20 | $0.35 | $0.53 | $0.20 |
| 2026-07-19 | $0.35 | $0.53 | $0.20 |
| 2026-07-18 | $0.35 | $0.53 | $0.20 |
| 2026-07-17 | $0.53 | – | $0.34 |
| 2026-07-16 | $0.53 | – | $0.34 |
| 2026-07-15 | $0.58 | – | $0.34 |
| 2026-07-14 | $0.69 | – | $0.34 |
| 2026-07-13 | $0.53 | – | $0.34 |
| 2026-07-12 | $0.53 | – | $0.34 |
| 2026-07-11 | $0.53 | – | $0.34 |
| 2026-07-10 | $0.58 | – | $0.34 |
| 2026-07-09 | $0.58 | – | $0.34 |
| 2026-07-08 | $0.58 | – | $0.34 |
| 2026-07-07 | $0.58 | – | $0.34 |
| 2026-07-06 | $0.58 | – | $0.34 |
| 2026-07-05 | $0.69 | – | $0.34 |
RTX 4090 prices by provider and billing type
Each provider's cheapest rate in each billing type, per GPU-hour. The provider name opens its RTX 4090 page with node sizes, fees and its own history.
| Provider | On-demand | Spot & community | Serverless |
|---|---|---|---|
| TensorDock | $0.35 | – | – |
| Spheron | $0.58 | – | – |
| RunPod | $0.89 | $0.34 | $1.10 |
| Daytona | $0.99 | $0.57 | – |
| SaladCloud | – | $0.16 | – |
RTX 4090 hardware specs
| Architecture | Ada Lovelace |
|---|---|
| VRAM | 24 GB |
| FP16 TFLOPS (dense) | 165 |
| Memory bandwidth | 1,008 GB/s |
| TDP | 450 W |
| Interconnect | PCIe Gen4 |
| Launched | 2022 |
Manufacturer datasheet figures for the RTX 4090. Source: www.nvidia.com.
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 ✓ |
| QwQ 32B | 79.9 | 40.6 | 20.9 ✓ |
| Qwen3 32B | 79.9 | 40.6 | 20.9 ✓ |
| Qwen3 30B A3B | 73.8 | 37.1 | 18.8 ✓ |
| Qwen3 30B A3B 2507 | 73.8 | 37.1 | 18.8 ✓ |
| Qwen3 Coder 30B A3B | 73.8 | 37.1 | 18.8 ✓ |
| Mistral Small 3.2 24B 2506 | 58.4 | 29.6 | 15.2 ✓ |
| Mistral Small 24B 2501 | 57.4 | 29.1 | 14.9 ✓ |
| Devstral Small 2507 | 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 ✓ |
| Phi 4 reasoning | 36.2 | 18.6 ✓ | 9.8 ✓ |
| Phi 4 reasoning plus | 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 ✓ |
| Qwen3 4B 2507 | 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 ✓ |
Models that need more than one RTX 4090
- Qwen2.5 72B at 16-bit needs about 176 GB with the same context and headroom, so at least 8 cards. No provider we track publishes a RTX 4090 node of that size today. At 8 or 4 bit it needs less; the model page recalculates.
- DeepSeek R1 Distill Llama 70B at 16-bit needs about 171 GB with the same context and headroom, so at least 8 cards. No provider we track publishes a RTX 4090 node of that size today. At 8 or 4 bit it needs less; the model page recalculates.
- Mixtral 8x7B v0.1 at 16-bit needs about 113 GB with the same context and headroom, so at least 5 cards. No provider we track publishes a RTX 4090 node of that size today. At 8 or 4 bit it needs less; the model page recalculates.
Compare model memory requirements or change context and memory assumptions on a model's page.
When to choose the RTX 4090, and what to pick instead
Start from memory: your model, its context and your batch must fit in 24 GB (the model-fit table above estimates it). Then the RTX 4090 is the right card unless one of these fits your job better.
- Pick the RTX 3090 (24 GB, from $0.20/hr) when your model fits in 24 GB and you can wait longer: it costs 43% less per hour.
- Pick the RTX 5090 (32 GB, from $0.35/hr) when the model or its cache does not fit in 24 GB, or finishing sooner is worth paying more: it has 1.3 times the RTX 4090's 16-bit compute.
Our workload guides recommend the RTX 4090 for 3D rendering, batch inference, cloud gaming and game streaming, computer vision, text embeddings, Jupyter notebooks, LLM fine-tuning, inference, speech recognition, Stable Diffusion & ComfyUI and AI video generation. Each compares it with the other cards that suit that job, at today's prices.
Answered from today's RTX 4090 prices: How much does an RTX 4090 cost to rent?
Rent or buy the RTX 4090
We have no confirmed RTX 4090 purchase price from the stores we check; renting starts at $0.35 per GPU-hour. A seller quote entered in the calculator gives the break-even.
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. Compare two GPUs.
RTX 4090 questions
- How much does it cost to rent a RTX 4090?
- The cheapest RTX 4090 rental we have is $0.35 per GPU-hour on TensorDock (on-demand), checked 22 October 2026. The median of each provider's cheapest on-demand rate is $0.73 across 4 providers.
- How much VRAM does a RTX 4090 have?
- 24 GB.
- Where is the RTX 4090 cheapest right now?
- TensorDock has the cheapest checked on-demand rate today at $0.35 per GPU-hour; interruptible spot or community capacity starts at $0.16 (SaladCloud).
GPUs near the RTX 4090
- A3024 GB$0.35/hrcheapest on-demand
- L424 GB$0.44/hrcheapest on-demand
- RTX A500024 GB$0.44/hrcheapest on-demand
- RTX 509032 GB$0.35/hrcheapest on-demand
- RTX PRO 400024 GB$0.57/hrcheapest on-demand
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 · Best Cloud GPU to Rent for 3D Rendering · Cloud GPU for batch inference · How much does an RTX 4090 cost to rent?