GPU Cloud Pricing · Ada Lovelace
The universal data center Ada card — 48 GB and strong FP8 throughput make it a favorite for mixed inference, fine-tuning, and rendering fleets.
GPU.ai rates are the live fleet floor — the cheapest provider with stock, passed through at cost. Competitor rates are public on-demand list prices.
| Provider | $ / GPU / hr |
|---|---|
| GPU.ai — Secure Cloud | $0.800 |
| GPU.ai — Community Cloud | $0.740 |
| CoreWeave | $1.24 |
| AWS | $1.52 |
| Azure | $2.50 |
Need scale? Real 4× L40S nodes are in inventory from $0.800/GPU/hr.
Available regions: Asia Pacific · Europe East · Europe West · US Central
GPU.ai prices are read live from our aggregated fleet of 12+ GPU clouds and normalized to a per-GPU hourly rate (a 4× node's price is divided by its GPU count). We charge the provider's raw rate with zero markup and bill per second. Competitor figures are each provider's public on-demand list rate for the closest equivalent SKU — never spot, reserved, or committed-use discounts. Stock counts reflect launchable inventory, not theoretical capacity. Last updated 2026-08-17; this page refreshes hourly.
| Architecture | Ada Lovelace |
| VRAM | 48 GB GDDR6 |
| Memory bandwidth | 864 GB/s |
| FP16 tensor (dense) | 183 TFLOPS |
| CUDA cores | 18,176 |
| Power (TDP) | 350 W |
| Interconnect | PCIe 4.0 |
| Released | 2023 |
Minimum L40S count needed to hold popular open models in VRAM, at FP16 and 4-bit quantization.
| Model | Params | FP16 | 4-bit |
|---|---|---|---|
| Llama 3.1 8B | 8B | 1× L40S | 1× L40S |
| Mistral 7B | 7B | 1× L40S | 1× L40S |
| Gemma 2 27B | 27B | 2× L40S | 1× L40S |
| Qwen2.5 32B | 32B | 2× L40S | 1× L40S |
| Llama 3.1 70B | 70B | 4× L40S | 1× L40S |
| Qwen2.5 72B | 72B | 4× L40S | 2× L40S |
| Mixtral 8x22B | 141B MoE | 8× L40S | 2× L40S |
| Llama 3.1 405B | 405B | Doesn't fit | 8× L40S |
| FLUX.1 dev | 12B | 1× L40S | 1× L40S |
| SDXL | 3.5B | 1× L40S | 1× L40S |
| Whisper large-v3 | 1.5B | 1× L40S | 1× L40S |
Weights-only estimates with a 20% margin for KV cache and activations at moderate context. Long contexts, large batches, and training need substantially more memory.
L40S cloud instances on GPU.ai currently start at $0.740 per GPU per hour, billed per second. That is the live floor price across every provider in our fleet — we route your launch to the cheapest provider with stock and add zero markup.
The NVIDIA L40S has 48 GB of GDDR6 memory with up to 864 GB/s of bandwidth. GPU.ai reports the minimum VRAM actually delivered across our fleet, so the figure you see at launch is the figure you get.
Yes — real 4× L40S nodes are launchable right now, from $0.800 per GPU per hour. We only advertise node sizes that exist in live inventory, not theoretical configurations.
GPU.ai aggregates a dozen-plus GPU clouds and passes through each provider's raw price with no markup, so the same silicon is typically far cheaper than hyperscaler list rates. The comparison table on this page shows the current public on-demand list prices side by side.
Billing is per second, starting when your instance is SSH-ready and stopping the moment you terminate. There are no minimum commitments, no reservation fees, and no egress surprises — you pay the listed hourly rate pro-rated to the second.