Cloud ProviderEst. 2022
RunPod Logo

RunPod GPU Pricing

A leader in democratized GPU space offering serverless inference and cost-effective experimentation.

94 Instances14 Regions88 Available
Visit RunPod

Lowest Price

$0.12/hr

NVIDIA RTX A2000

Live Inventory

Real-time GPU availability on RunPod

94 offers available
RunPod
RunPod
🌍global
NVIDIA RTX A2000
12GB VRAM
6 vCPU
20GB RAM
$0.12/GPU/hr
RunPod
RunPod
🌍global
NVIDIA GeForce RTX 3070
8GB VRAM
6 vCPU
30GB RAM
$0.13/GPU/hr
RunPod
RunPod
🌍global
NVIDIA RTX A5000
24GB VRAM
9 vCPU
25GB RAM
$0.16/GPU/hr
RunPod
RunPod
🌍global
NVIDIA GeForce RTX 3080
10GB VRAM
8 vCPU
50GB RAM
$0.17/GPU/hr
RunPod
RunPod
🌍global
NVIDIA RTX A4000
16GB VRAM
8 vCPU
25GB RAM
$0.17/GPU/hr
View all 94 offers

GPU Models on RunPod

RunPod offers 39 GPU models. Select one for detailed pricing.

RTX A2000
12GB VRAM
$0.12/hr
RTX 3070
8GB VRAM
$0.13/hr
RTX A5000
24GB VRAM
$0.16/hr
RTX A4000
16GB VRAM
$0.17/hr
RTX 3080
10GB VRAM
$0.17/hr
RTX 4000 Ada Generation
20GB VRAM
$0.18/hr
RTX 3080 Ti
12GB VRAM
$0.18/hr
RTX 4070 Ti
12GB VRAM
$0.19/hr
Tesla V100 16GB
16GB VRAM
$0.19/hr
RTX A4500
20GB VRAM
$0.19/hr
RTX 3090
24GB VRAM
$0.22/hr
A30
24GB VRAM
$0.22/hr
RTX 2000 Ada Generation
16GB VRAM
$0.24/hr
RTX 4080
16GB VRAM
$0.27/hr
RTX 3090 Ti
24GB VRAM
$0.27/hr
RTX 4080 SUPER
16GB VRAM
$0.28/hr
Tesla V100 32GB
32GB VRAM
$0.33/hr
RTX A6000
48GB VRAM
$0.33/hr
RTX 4500 Ada
24GB VRAM
$0.34/hr
RTX 4090
24GB VRAM
$0.34/hr
A40
48GB VRAM
$0.35/hr
L4
24GB VRAM
$0.39/hr
RTX 5080
16GB VRAM
$0.39/hr
RTX 5000 Ada Generation
32GB VRAM
$0.49/hr
MI300X
192GB VRAM
$0.50/hr
RTX 6000 Ada Generation
48GB VRAM
$0.50/hr
H200 NVL
141GB VRAM
$0.50/hr
L40
48GB VRAM
$0.69/hr
RTX 5090
32GB VRAM
$0.69/hr
L40S
48GB VRAM
$0.79/hr
A100 SXM4 40GB
40GB VRAM
$1.00/hr
A100 PCIe 40GB
40GB VRAM
$1.19/hr
A100 SXM4 80GB
80GB VRAM
$1.39/hr
H100 PCIe
80GB VRAM
$1.99/hr
H100 NVL
94GB VRAM
$2.59/hr
H100 SXM5
80GB VRAM
$2.69/hr
H200 SXM
141GB VRAM
$3.59/hr
B200 SXM
192GB VRAM
$4.99/hr
B300 SXM6
262GB VRAM
$6.94/hr

About RunPod

Founded 2022
Moorestown, New Jersey

Best For

Serverless inferenceCost-effective experimentation

Unique Features

  • Dual-tier model (Community vs. Secure)
  • FlashBoot technology

Platform Features

Access Methods
FeatureAvailable
SSH Access
Jupyter Notebooks
Web Terminal
API Access
Kubernetes
Containers
Billing Options
FeatureAvailable
Billing Incrementper-second
Spot Instances
Reserved Instances
Prepaid Credits
Compliance
CertificationCertified
SOC 2
HIPAA
GDPR
ISO 27001
Support
FeatureAvailable
SLA Guarantee
Enterprise Support
Discord Community

RunPod Pricing Breakdown

▾

RunPod offers 39 GPU types with on-demand pricing ranging from $0.12/hr for the RTX A2000 to $7.39/hr for the B300 SXM6. 88 of 94 instances are currently in stock across 14 regions.

Billing on RunPod is per per-second. Spot instances are available for workloads that can tolerate interruption, typically at 50-80% lower cost than on-demand rates.

Alternatives to RunPod

▾

GPUPerHour tracks over 25 cloud GPU providers. RunPod starts at $0.12/hr for the RTX A2000, but pricing and availability vary across providers. The best alternative depends on your requirements: GPU model, region, compliance certifications, and billing flexibility all differ between providers.

For head-to-head analysis, see: RunPod vs Salad, RunPod vs Scaleway, RunPod vs TensorDock. The comparison tool covers all provider matchups.

Frequently Asked Questions

▾
How much does RunPod charge for GPUs?▾

RunPod GPU pricing starts at $0.12/hr for the RTX A2000 and goes up to $7.39/hr for the B300 SXM6. Billing is per per-second. Prices are updated every 60 seconds on GPUPerHour.

What GPUs are available on RunPod?▾

RunPod offers 39 GPU types with 94 total instances. The most common models are: RTX 6000 Ada Generation (8 offers), RTX 4000 Ada Generation (6 offers), H200 SXM (6 offers), A100 SXM4 80GB (4 offers), H100 SXM5 (4 offers).

Does RunPod offer spot pricing?▾

Yes, RunPod offers spot instances with discounted pricing. Spot instances can be reclaimed when demand is high, making them best suited for fault-tolerant workloads like batch training or data preprocessing.

What regions does RunPod operate in?▾

RunPod has GPU instances available across 14 regions. Region selection affects both latency and pricing. Use the filters on GPUPerHour to find instances in a specific location.

How does RunPod compare to alternatives?▾

RunPod prices start at $0.12/hr, with 39 GPU types across 14 regions. GPUPerHour tracks pricing from over 25 cloud GPU providers, making it possible to compare RunPod against alternatives on price, GPU selection, and availability in real time.

Does RunPod have compliance certifications?▾

RunPod holds SOC 2, HIPAA, GDPR certifications. Compliance certifications are important for organizations handling sensitive data or operating in regulated industries.

RunPod GPU Pricing: 39 GPUs from $0.12/hr (2026) | GPUPerHour