We raised 20M to revolutionize AI/ML cloud computing
Learn more

GPU Cloud
Pricing

Powerful & cost-effective GPUs built to support any workload.
GPUs are billed by the minute. No fees for ingress/egress.
Thousands of GPUs across 30+ Regions
Deploy any container on Secure Cloud. Public and private image repos are supported. Configure your environment the way you want.
Zero fees for ingress/egress
Global interoperability
99.99% Uptime
$0.05/GB/month Network Storage
Multi-region Support

192GB VRAM

amd
Starting from $4.89/hr

MI300X
192GB VRAM
283GB RAM
24 vCPUs
$4.89/hr
Secure Cloud

80GB VRAM

nvidia
Starting from $3.19/hr

H100 PCIe
80GB VRAM
188GB RAM
16 vCPUs
$3.69/hr
Secure Cloud
$3.19/hr
Community Cloud
nvidia
Starting from $3.89/hr

H100 SXM
80GB VRAM
125GB RAM
24 vCPUs
$4.69/hr
Secure Cloud
$3.89/hr
Community Cloud
nvidia
Starting from $1.49/hr

A100 PCIe
80GB VRAM
83GB RAM
8 vCPUs
$1.89/hr
Secure Cloud
$1.49/hr
Community Cloud
nvidia
Starting from $2.19/hr

A100 SXM
80GB VRAM
125GB RAM
16 vCPUs
$2.19/hr
Secure Cloud

48GB VRAM

nvidia
Starting from $0.67/hr

A40
48GB VRAM
48GB RAM
9 vCPUs
$0.69/hr
Secure Cloud
$0.67/hr
Community Cloud
nvidia
Starting from $1.14/hr

L40
48GB VRAM
250GB RAM
16 vCPUs
$1.14/hr
Secure Cloud
nvidia
Starting from $1.09/hr

L40S
48GB VRAM
62GB RAM
8 vCPUs
$1.34/hr
Secure Cloud
$1.09/hr
Community Cloud
nvidia
Starting from $0.69/hr

RTX A6000
48GB VRAM
50GB RAM
8 vCPUs
$0.79/hr
Secure Cloud
$0.69/hr
Community Cloud
nvidia
Starting from $0.99/hr

RTX 6000 Ada
48GB VRAM
62GB RAM
16 vCPUs
$1.14/hr
Secure Cloud
$0.99/hr
Community Cloud

24GB VRAM AND UNDER

nvidia
Starting from $0.26/hr

RTX A5000
24GB VRAM
24GB RAM
4 vCPUs
$0.44/hr
Secure Cloud
$0.26/hr
Community Cloud
nvidia
Starting from $0.54/hr

RTX 4090
24GB VRAM
24GB RAM
6 vCPUs
$0.74/hr
Secure Cloud
$0.54/hr
Community Cloud
nvidia
Starting from $0.26/hr

RTX 3090
24GB VRAM
24GB RAM
4 vCPUs
$0.44/hr
Secure Cloud
$0.26/hr
Community Cloud
nvidia
Starting from $0.29/hr

RTX 3090 Ti
24GB VRAM
???GB RAM
??? vCPUs
$0.29/hr
Community Cloud
nvidia
Starting from $0.26/hr

A30
24GB VRAM
31GB RAM
8 vCPUs
$0.26/hr
Community Cloud
nvidia
Starting from $0.21/hr

RTX A4500
20GB VRAM
29GB RAM
4 vCPUs
$0.36/hr
Secure Cloud
$0.21/hr
Community Cloud
nvidia
Starting from $0.21/hr

RTX A4000 Ada
20GB VRAM
31GB RAM
5 vCPUs
$0.39/hr
Secure Cloud
$0.21/hr
Community Cloud
nvidia
Starting from $0.19/hr

RTX A4000
16GB VRAM
19GB RAM
5 vCPUs
$0.34/hr
Secure Cloud
$0.19/hr
Community Cloud
nvidia
Starting from $0.00/hr

RTX 3080
10GB VRAM
15GB RAM
7 vCPUs
$0.18/hr
Community Cloud
nvidia
Starting from $0.00/hr

RTX 3070
8GB VRAM
14GB RAM
8 vCPUs
$0.14/hr
Community Cloud

Storage
Pricing

Flexible and cost-effective storage for every workload. No fees for ingress/egress.
Persistent and temporary storage available.
Over 100PB of storage available across North America and Europe.
Customize your pod volume and container disk in a few clicks, and access additional persistent storage with network volumes.
Zero fees for ingress/egress
Global interoperability
NVMe SSD
Multi-Region Support

Pod Storage

Storage TypeRunning PodsIdle Pods
Volume$0.10/GB/Month$0.20/GB/Month
Container Disk$0.10/GB/Month$0.20/GB/Month

Persistent Network Storage

Storage TypeUnder 1TBOver 1TB
Network Volume$0.07/GB/Month$0.05/GB/Month

Serverless
Pricing

Save 15% over other Serverless cloud providers on flex workers alone.
Create active workers and configure queue delay for even more savings.
80 GB
A100
Extremely performant GPUs, yet still very cost effective for running any machine learning model.
Flex
$0.0013/s
Active
$0.00078/s
80 GB
H100
PRO
Our most powerful GPUs. Most useful when maximizing inference throughput is critical.
Flex
$0.0025/s
Active
$0.0015/s
48 GB
A6000
A cost-effect option for running diffusion models, LoRAs, whisper, and many others. Less effective for large language models.
Flex
$0.00048/s
Active
$0.00029/s
48 GB
L40
PRO
Useful for when having high inference throughput on LLMs like Llama 3 7B and medium sized models like Yi 34B.
Flex
$0.00069/s
Active
$0.00041/s
24 GB
A5000
Great for small-to-medium sized models with consistent workloads, lower throughput than 24GB PRO.
Flex
$0.00026/s
Active
$0.00016/s
24 GB
4090
PRO
Extremely high throughput for small to medium sized models.Great for running Llama3 8B and Mistral 7B.
Flex
$0.00044/s
Active
$0.00026/s
16 GB
A4000
The most cost-effective option for running inference on small models like LoRAs, diffusion models, and whisper.
Flex
$0.0002/s
Active
$0.00012/s
North America
UR-OR-1
CA-MTL-1
CA-MTL-2
European Union
EUR-IS-1
EUR-IS-2
EUR-NO-1
Europe
EU-NL-1
EU-RO-1
EU-SE-1
Serverless Pricing Calculator
seconds
$ 55 /mo
1
72,000 requests per month
1. Cost estimation includes 50% of the requests using active price & running into 1s cold-start.
Are you an early-stage startup or ML researcher?
Get up to $25K in free compute credits with Runpod. These can be used towards on-demand GPUs and Serverless endpoints.
Apply
We're with you from seed to scale
Book a call with our sales team to learn more.
Gain
Additional Savings
with Reservations
Save more by committing to longer-term usage. Reserve discounted active and flex workers by speaking with our team.
Book a call