What are the lowest rates on Nebius AI Studio?

The cheapest hourly rate on Nebius AI Studio starts from $0.65/hr on spot capacity.

Does Nebius AI Studio charge for stopped storage?

When stopped, persistent storage is billed at approximately $0.07/GB/month NVMe until the volume is deleted.

Nebius AI Studio GPU Pricing & Hourly Rates

Verified RatesTier 3 InfiniBand Datacenter

Real-time verified rates (Updated 2026)

Cost Simulator Compare Rivals Deploy on Nebius AI Studio

Lowest Spot Rate$0.65/hr

Lowest On-Demand$0.89/hr

Billing IncrementPer Second

Stopped Volume Fee$0.07/GB/month NVMe

Nebius AI Studio Serverless AI Token Pricing (3 Models)

Compare Token Rates Across All APIs →

Model	Category	Cold Start	Context	Input ($/1M or Unit)	Output / 1M Tokens	Speed	Actions
Qwen-2.5-Coder-32B-Instruct	LLM	0s Instant	128K	$0.20	$0.25	90 tps	API Docs
Llama-3.3-70B-Instruct	LLM	0s Instant	128K	$0.35	$0.40	85 tps	API Docs
DeepSeek-R1	LLM	0s Instant	160K	$0.80	$2.40	70 tps	API Docs

All Available Nebius AI Studio GPU Instances (6 Tiers)

Click any GPU model to see live cross-cloud price comparisons against RunPod, TensorDock, Lambda Labs, and AWS.

Currency: USD ($/hour)

GPU Model & Specs	VRAM	Interconnect	vCPU / System RAM	Spot Hourly	On-Demand Hourly	Cost / GB VRAM	Actions
NVIDIA L40S 48GB	48 GB	PCIe 4.0 x16	12 vCPUs / 64GB	$0.65/hr-27%	$0.89/hr	$0.019/hr	Compare Deploy
NVIDIA A100 SXM4 80GB	80 GB	NVLink (Fast)	16 vCPUs / 128GB	$1.20/hr-25%	$1.60/hr	$0.020/hr	Compare Deploy
NVIDIA H100 SXM5 80GB	80 GB	NVLink (Fast)	32 vCPUs / 256GB	$1.85/hr-24%	$2.45/hr	$0.031/hr	Compare Deploy
8x NVIDIA L40S 48GB	384 GB	PCIe 4.0 x16	96 vCPUs / 512GB	$5.20/hr-27%	$7.12/hr	$0.019/hr	Compare Deploy
8x NVIDIA A100 SXM4 80GB	640 GB	NVLink (Fast)	128 vCPUs / 1024GB	$9.60/hr-25%	$12.80/hr	$0.020/hr	Compare Deploy
8x NVIDIA H100 SXM5 80GB	640 GB	NVLink (Fast)	128 vCPUs / 1024GB	$14.80/hr-24%	$19.60/hr	$0.031/hr	Compare Deploy

Estimate Your Monthly Cloud Bill

Simulate active daily compute hours, stopped persistent disk fees, and compare total monthly cost on Nebius AI Studio versus RunPod and AWS EC2.

Open Nebius AI Studio Cost Calculator

Compare Top Nebius AI Studio Rivals

Check competing platforms like RunPod, TensorDock, and Lambda Labs to find lower storage fees or dedicated enterprise Tier 3 datacenters.

View Alternatives Comparison

Nebius AI Studio Pricing FAQ & Cost Guide

How do Nebius AI Studio Spot vs On-Demand rates work?

On-demand instances give you uninterrupted compute until you voluntarily stop or terminate them. Spot instances offer dramatic discounts (typically 20% to 60% off), but may be interrupted or evicted if a higher-paying user bids on the host. Always enable automatic model checkpointing when using spot capacity.

Does Nebius AI Studio charge for stopped instances or idle storage?

Yes. When an instance is stopped, GPU compute billing halts immediately, but attached persistent volumes continue to accrue storage fees ($0.07/GB/month NVMe). To avoid unexpected charges, terminate instances or offload weights to S3/Cloudflare R2 when not in active use.

Are there hidden egress or bandwidth fees?

Egress on Nebius AI Studio is billed at Free inside VPC.

What payment methods does Nebius AI Studio accept?

Nebius AI Studio accepts standard credit card billing and enterprise invoicing with verified business accounts.