NVIDIA A100 PCIe cloud GPU rental
Rent an NVIDIA A100 PCIe cloud GPU from $1.29 per hour with 80 GB of HBM2e at 1.9 TB/s of memory bandwidth. FastInfra bills pods per minute with no commitment, so a one-hour experiment costs $1.29 and you stop paying the moment you delete the pod. Run 1 to 8 GPUs per pod, connect over SSH or JupyterLab, and see the exact price before you deploy.
Prices synced November 3, 2026 · billed per minute
A100 PCIe specs and pricing
The NVIDIA A100 PCIe is a datacenter Ampere GPU with 80 GB of HBM2e at 1.9 TB/s of memory bandwidth. On FastInfra it is a good fit for 70B+ inference, multi-node training, large-batch fine-tuning. As a rule of thumb, one A100 PCIe holds the weights of a model of about 32B parameters at 16-bit precision, or about 120B with 4-bit quantization, after leaving room for the KV cache.
Two on-demand tiers are available. Secure runs in vetted datacenters at $1.93 per GPU-hour; Value uses lower-cost community hosts at $1.29 per GPU-hour for the same GPU model, with more variable capacity.
A100 PCIe price per hour by GPU count
Live FastInfra prices per pod-hour. Pods bill per minute, so you pay only for the minutes a pod exists.
| Pod size | Total VRAM | Secure / hr | Value / hr | Month (730 h, lowest) |
|---|---|---|---|---|
| 1× A100 PCIe | 80 GB | $1.93 | $1.29 | $939 |
| 2× A100 PCIe | 160 GB | $3.87 | $2.57 | $1,878 |
| 4× A100 PCIe | 320 GB | $7.74 | $5.14 | $3,755 |
| 8× A100 PCIe | 640 GB | $15.47 | — | $11,295 |
What an A100 PCIe costs over time
One GPU at the lowest on-demand rate ($1.29/hr).
| Duration | On-demand |
|---|---|
| 1 hour | $1.29 |
| 8-hour working day | $10.29 |
| 24 hours | $30.86 |
| 1 week (168 hours) | $216 |
| 1 month (730 hours) | $939 |
Which LLMs fit on the A100 PCIe?
GPUs needed to hold the model weights with about 20% of VRAM left for the KV cache. Rule of thumb only: long contexts and big batches need more.
| Model size | Examples | FP16 / BF16 | 8-bit | 4-bit |
|---|---|---|---|---|
| 7–8B | Llama 3.1 8B, Qwen3 8B, Mistral 7B | 1 GPU | 1 GPU | 1 GPU |
| 12–14B | Gemma 3 12B, Qwen3 14B, Phi-4 | 1 GPU | 1 GPU | 1 GPU |
| 27–32B | Gemma 3 27B, Qwen3 32B | 1 GPU | 1 GPU | 1 GPU |
| 70B | Llama 3.3 70B | 4 GPUs | 2 GPUs | 1 GPU |
| 120B | GPT-OSS 120B | 4 GPUs | 2 GPUs | 1 GPU |
| 235B | Qwen3 235B-A22B | 8 GPUs | 4 GPUs | 2 GPUs |
| 405B | Llama 3.1 405B | Needs more GPUs | 8 GPUs | 4 GPUs |
| 671B | DeepSeek V3 / R1 | Needs more GPUs | Needs more GPUs | 8 GPUs |
Best for
70B+ inference, multi-node training, large-batch fine-tuning.
About the Ampere architecture
Ampere brought third-generation Tensor Cores with BF16 and TF32 support, which modern training code relies on, and the A100 added Multi-Instance GPU partitioning. Ampere cards remain a dependable, lower-cost option for fine-tuning, inference and research, though they lack the FP8 support of Ada, Hopper and Blackwell.
Only need inference?
If you want to call an open model such as Llama, Qwen, DeepSeek or GPT-OSS rather than manage a server, the pay-per-token inference API is often cheaper than keeping a GPU busy around the clock. It is OpenAI-compatible and uses the same account and wallet as your pods. Browse every model with live prices.
A100 PCIe vs similar GPUs
Live lowest on-demand price per GPU-hour, and price per GB of VRAM.
| GPU | VRAM | Architecture | From / hr | Per GB-hr |
|---|---|---|---|---|
| A100 PCIe (this page) | 80 GB | Ampere | $1.29 | $0.016 |
| NVIDIA RTX PRO 6000 Max-Q | 96 GB | Blackwell | $1.77 | $0.018 |
| NVIDIA RTX PRO 6000 | 96 GB | Blackwell | $1.83 | $0.019 |
| NVIDIA H100 NVL | 94 GB | Hopper | $2.80 | $0.03 |
| NVIDIA A100 SXM | 80 GB | Ampere | $1.50 | $0.019 |
| NVIDIA H100 PCIe | 80 GB | Hopper | $2.15 | $0.027 |
| NVIDIA H100 SXM | 80 GB | Hopper | $2.91 | $0.036 |
A100 PCIe rental — frequently asked questions
How much does it cost to rent an NVIDIA A100 PCIe per hour?
$1.93 per GPU-hour on the Secure tier and $1.29 on the Value tier. Billing is per minute while the pod exists, so 24/7 use for a 730-hour month costs about $939 per GPU at the lowest on-demand rate. Prices sync from live capacity and are shown before you deploy.
How much VRAM does the NVIDIA A100 PCIe have?
80 GB of HBM2e at 1.9 TB/s of memory bandwidth. The chip is rated at up to 300 W. A pod with 8 GPUs gives 640 GB of combined VRAM for tensor- or pipeline-parallel workloads.
What size LLM can I run on an NVIDIA A100 PCIe?
Roughly 32B parameters at FP16 or BF16, 64B at 8-bit and 120B at 4-bit on a single GPU, reserving about 20% of VRAM for the KV cache and activations. Mixture-of-experts models need memory for all experts, not only the active ones. Long contexts and large batches need more headroom.
Is the NVIDIA A100 PCIe billed per hour or per minute?
Per minute. The hourly rate is divided by 60 and charged for every minute the pod exists. Attached volumes bill per GB-month and continue while a pod is stopped; delete the pod to stop all charges. There is no minimum term or reservation fee.
How do I rent an NVIDIA A100 PCIe on FastInfra?
Create an account, add prepaid credit, open the GPU configurator and choose the A100 PCIe, the tier, the GPU count, a container template and storage. The configurator shows the hourly and monthly price, then deploys a pod you reach over SSH or JupyterLab within minutes.
Can I rent multiple A100 PCIe GPUs in one pod?
Yes, up to 8 per pod (8 on Secure, 6 on Value). The price scales linearly: 8 GPUs cost $15.47 per hour on Secure.
Deploy an A100 PCIe in minutes
Price the exact pod, storage and template in the configurator, add credit, and connect over SSH or JupyterLab. Billed per minute, no commitment.