Rent an NVIDIA RTX 4070 Ti SUPER from $0.06 per GPU-hour
NVIDIA RTX 4070 Ti SUPER cloud rental: $0.06 per GPU-hour on spot, $0.09 on-demand, $0.06 reserved, billed by the minute. RTX 4070 Ti SUPER is a consumer board rented by the hour with 16 GB of GDDR6X, built on the Ada Lovelace architecture in 2024. It holds models up to about 6B at FP16, and 13B-class models quantised.
Billed per started minute. 64 GB of GPU memory on a 4× node. Persistent storage $0.08 per GB-month. No egress fees.
- GPU memory
- 16GBGDDR6X
- Node sizes
- 1× · 2× · 4×Same price per GPU at every size
- Reclaim rate
- 10–15%Spot instances reclaimed over 30 days
What you get with each RTX 4070 Ti SUPER node.
| Node | GPU memory | vCPU | RAM | Local NVMe | Spot | On-demand | Action |
|---|---|---|---|---|---|---|---|
| 1× RTX 4070 Ti SUPER | 16 GB | 6 | 32 GB | 500 GB | $0.06/h | $0.09/h | Configure |
| 2× RTX 4070 Ti SUPER | 32 GB | 12 | 64 GB | 1 TB | $0.12/h | $0.18/h | Configure |
| 4× RTX 4070 Ti SUPER | 64 GB | 24 | 128 GB | 2 TB | $0.24/h | $0.36/h | Configure |
GPU-to-GPU link: PCIe Gen4 x16. Local NVMe is scratch space wiped when the instance ends; keep anything you need on a persistent disk.
24 RTX 4070 Ti SUPER GPUs free right now.
Straight from the capacity pool the console books against. Prices are identical in every region — pick the one closest to your data.
A region with zero free GPUs still accepts reserved capacity requests — we hold hardware for a term rather than sell what is already taken.
What fits in 16 GB — and what it costs per hour.
Weights need about 2 GB per billion parameters at FP16 / BF16, 1 GB per billion parameters at FP8, 0.5 GB per billion parameters at INT4. We keep 20% of the memory free for activations, the KV cache and the CUDA context, then take the smallest node that still fits.
| Open model | Parameters | FP16 / BF16node · spot price | FP8node · spot price | INT4node · spot price |
|---|---|---|---|---|
| Llama 3.1 8BThe default small model for fine-tuning and agents | 8B | 2× $0.12/h | 1× $0.06/h | 1× $0.06/h |
| Qwen3 14BMid-size dense Qwen3 | 14.8B | 4× $0.24/h | 2× $0.12/h | 1× $0.06/h |
| gpt-oss-20bSmall open-weight reasoning model for local and edge serving | 21B | 4× $0.24/h | 2× $0.12/h | 2× $0.12/h |
| Gemma 4 31BLargest dense Gemma 4, multimodal, 256K context | 31.3B | over 4× | 4× $0.24/h | 2× $0.12/h |
| Qwen3.6 35B A3BSmall hybrid-attention mixture of experts | 35B | over 4× | 4× $0.24/h | 2× $0.12/h |
| Llama 3.3 70BThe common 70B baseline (same size and layout as Llama 3.1 70B) | 70.6B | over 4× | over 4× | 4× $0.24/h |
| gpt-oss-120bOpen-weight reasoning model, mixture of experts, tool use | 117B | over 4× | over 4× | over 4× |
| Qwen3 235B A22BFlagship Qwen3 mixture of experts, the 2507 checkpoint | 235B | over 4× | over 4× | over 4× |
| DeepSeek R1Reasoning model, the R1-0528 checkpoint | 671B | over 4× | over 4× | over 4× |
Each model links to its full sizing: KV cache by context length and every GPU that runs it — GPU requirements for 64 open models.
Real usage depends on context length, batch size and the serving engine: a long context can add tens of gigabytes of KV cache. Treat the table as the floor, not the ceiling — and if a job is close to the limit, take the next node size or quantise one step further.
What a dollar buys on an RTX 4070 Ti SUPER.
Ranked 12 of 14 consumer models in this catalogue on cost per gigabyte of GPU memory.
GPU memory you get for $1.00 of spot time, per hour.
Spot price divided by published FP32 throughput.
One GPU on spot, billed per minute, storage excluded.
Against the rest of the market
5 providers · September 2026- Median on-demand elsewhere
- $0.21Our on-demand is 57% below it
- Cheapest on-demand seen
- $0.12Our on-demand $0.09 is 25% below it
- Cheapest spot seen
- $0.09Our spot $0.06 is 33% below it
- 24 hours on one GPU
- $1.44 on spot$2.16 on-demand · $2.88 at the cheapest rate found elsewhere
Index built from published prices for the same GPU across 102 providers (provider pricing pages and public price indexes), September 2026. How the guarantee is enforced.
RTX 4070 Ti SUPER price per hour at 4 other providers.
The lowest published on-demand rate we recorded at each provider, cheapest first: $0.12 to $0.46 per GPU-hour, with a median of $0.20. Every row links to its source; a provider without a published price is left out rather than estimated.
| # | Provider | On-demandper GPU-hour | Spot | 730 h | Source |
|---|---|---|---|---|---|
| — | OnlineGPUthis site · how the price is set | $0.09 | $0.06 | $65.70 | pricing page |
| 1 | Vast.airecorded 15 Sep 2026 | $0.12 | $0.10 | $87.60 | getdeploying.com |
| 2 | Liumrecorded 15 Sep 2026 | $0.18 | not published | $131.40 | lium.io |
| 3 | Saladrecorded 15 Sep 2026 | $0.21 | $0.09 | $153.30 | getdeploying.com |
| 4 | Theta EdgeCloudrecorded 15 Sep 2026 | $0.46 | not published | $335.80 | getdeploying.com |
Recorded 15 September 2026 from published price pages (provider pricing pages and public price indexes), compute only: storage, egress and taxes excluded. Prices move — if a row is out of date, send us the link and it is corrected.
What people run on an RTX 4070 Ti SUPER.
Quantised inference
Small and medium models in 4-bit or 8-bit form, with the whole model resident in memory.
Computer vision and batch jobs
Detection, classification, embeddings and transcoding at a very low hourly rate.
Anything that can checkpoint
On the spot tier this model is 33% below its own on-demand price, with a 2-minute notice before a reclaim.
NVIDIA RTX 4070 Ti SUPER, as published by NVIDIA.
Taken from the vendor datasheet. Where a figure is not published, the row is absent rather than estimated.
- Vendor
- NVIDIA
- Architecture
- Ada Lovelace (2024)
- Segment
- Consumer
- Memory
- 16 GB GDDR6X
- FP32
- 44 TFLOPS
- CUDA cores
- 8,448
- Board power
- 285 W
- Form factor
- PCIe
- Interconnect
- PCIe Gen4 x16
- Multi-instance (MIG)
- Not available
- 8-bit float (FP8)
- Supported by the architecture
Source: www.nvidia.com · not confirmed on a vendor document
Software that runs on it
8 templatesPre-built environments, pulled on the node before you land on it. Or bring any OCI image from a public or private registry.
On the spot tier
10–15% reclaimed · 30 d- 2 minutes of notice on the metadata endpoint, a webhook and the console
- The instance is stopped, not deleted — disk and IP stay attached
- Auto-relaunch on the next free RTX 4070 Ti SUPER, or switch the same disk to on-demand
- You save $0.72 a day per GPU against on-demand
If the RTX 4070 Ti SUPER is not the right fit.
Same memory or more, 17% cheaper on spot
RTX 4000 Ada 20 GB GDDR6 · Ada Lovelace $0.06/h spotNext step up in memory: 20 GB instead of 16 GB
RTX 4090 24 GB GDDR6X · Ada Lovelace $0.06/h spotSame Ada Lovelace generation
RTX 4080 SUPER 16 GB GDDR6X · Ada Lovelace $0.06/h spotSame Ada Lovelace generation
Or put two of them side by side: RTX 4070 Ti SUPER vs RTX 3090 · RTX 4070 Ti SUPER vs RTX 4000 Ada · RTX 4070 Ti SUPER vs RTX 4090
RTX 4070 Ti SUPER — the questions that come up
How much does an RTX 4070 Ti SUPER cost per hour?
Spot is $0.06 per GPU-hour and on-demand is $0.09, both billed per minute — every started minute costs the hourly price divided by 60, so $0.0010 on spot. Reserved capacity is $0.06 per GPU-hour on a monthly commitment. Storage and egress are not included in that rate: persistent disks are $0.08 per GB-month and there are no egress fees.
How many GPUs can I put in one instance?
Node sizes are 1×, 2×, 4× — up to 4 RTX 4070 Ti SUPER GPUs in a single virtual machine, with CPU, RAM and local NVMe scaled with the GPU count. The price per GPU is identical at every node size.
Can it run a 70B model?
Not on a single node of this model: at FP8 a 70B model needs about 70 GB of memory for the weights alone, more than 4× 16 GB leaves free. Quantised to 4 bits it needs about 35 GB — check the memory table above — or pick a model with more memory per GPU.
Which regions have it?
Available now in US West (Oregon). Prices are identical in every region; pick the one closest to your data.
How often is a spot RTX 4070 Ti SUPER reclaimed?
Over the trailing 30 days, 10–15% of spot instances on this model were reclaimed. You get a 2-minute notice on the metadata endpoint, through a webhook and in the console; the instance is then stopped, never deleted, and the persistent disk stays attached.
Anything else about this model? Ask an engineer — the same people run the nodes. See also all prices, how we compare with 41 other providers and how to pay in crypto.
An RTX 4070 Ti SUPER for $0.06 an hour, running in under 60 seconds.
Prepaid in crypto, pay as you go: no card, no contract, no minimum commitment. Add credit, launch, stop whenever you want.
Billed per minute from the moment the instance is reachable. Minimum credit $30, no subscription. 24 RTX 4070 Ti SUPER GPUs available right now.