About RunPod

Looking for a powerful and reliable cloud solution that is specifically built for production? Look no further than RunPod. The cloud platform offers global distribution, making it easily accessible from anywhere in the world. With RunPod, one can run AI inference and training with ease, automating the workflow and spinning up GPUs on the fly in a matter of seconds. With Spot GPUs, allows to take advantage of low prices and save up to 50% on the compute jobs. For tasks that require consistent reliability with no interruptions, OnDemand GPUs are always available for use. At RunPod, value flexibility and convenience. That's why the softwares provides multiple access points to code, optimize, and run the AI/ML jobs. But what sets us apart is the ability to stop pods and resume them later while keeping the data safe. This feature is especially useful for long-running jobs or tasks that require frequent interruptions. Choose RunPod and experience the power, flexibility, and convenience of a global cloud built specifically for AI.

Pricing

Free Trial Not Available
RunPod Offers Custom plan.
View Detailed Pricing

Platforms Supported

Browser Based (Cloud)

Organization Types Supported

All (Small, Medium, Large)

API Support

Available

Modes of Support

Online

RunPod Pricing

Free Trial

Not available

Pricing Options

Freemium ( Limited Features )

Premium Plans ( Subscription / Quotation Based )

Pricing Plans

GPU Instance Others

1. A100 80GB:

80 GB VRAM
125 GB RAM
8 vCPU

On-Demand

1x GPU $/hr: 1.99
8x GPU $/hr: 15.92

2. A100 SXM 80GB:

80 GB VRAM
125 GB RAM
16 vCPU

On-Demand

1x GPU $/hr: 2.29
8x GPU $/hr: 18.32

3. H100 80GB SXM5:

80 GB VRAM
251 GB RAM
26 vCPU

On-Demand

1x GPU $/hr: 4.69
8x GPU $/hr: 37.52

4. H100 80GB PCIe

80 GB VRAM
250 GB RAM
16 vCPU

On-Demand

1x GPU $/hr: 4.49
8x GPU $/hr: 35.92

5. A40

48 GB VRAM
50 GB RAM
9 vCPU

Spot

1x GPU $/hr: 0.49
8x GPU $/hr: 3.92

On-Demand

1x GPU $/hr: 0.79
8x GPU $/hr: 6.32

1 Month

1x GPU $/hr: 0.75
8x GPU $/hr: 6

3 Month

1x GPU $/hr: 0.71
8x GPU $/hr: 5.68

6 Month

1x GPU $/hr: 0.67
8x GPU $/hr: 5.36

5. L40

48 GB VRAM
250 GB RAM
16 vCPU

Spot

1x GPU $/hr: 0.69
8x GPU $/hr: 5.52

On-Demand

1x GPU $/hr: 1.14
8x GPU $/hr: 9.12

1 Month

1x GPU $/hr: 1.08
8x GPU $/hr: 8.64

3 Month

1x GPU $/hr: 1.02
8x GPU $/hr: 8.16

6 Month

1x GPU $/hr: 0.97
8x GPU $/hr: 7.76

6. RTX 6000 Ada

48 GB VRAM
61 GB RAM
8 vCPU

On-Demand

1x GPU $/hr: 1.14
8x GPU $/hr: 9.12

7. RTX A6000

48 GB VRAM
50 GB RAM
8 vCPU

Spot

1x GPU $/hr: 0.49
8x GPU $/hr: 3.92

On-Demand

1x GPU $/hr: 0.79
8x GPU $/hr: 6.32

1 Month

1x GPU $/hr: 0.75
8x GPU $/hr: 6

3 Month

1x GPU $/hr: 0.71
8x GPU $/hr: 5.68

6 Month

1x GPU $/hr: 0.67
8x GPU $/hr: 5.36

8. RTX 3090

24 GB VRAM
27 GB RAM
4 vCPU

On-Demand

1x GPU $/hr: 0.44
8x GPU $/hr: 3.52

9. RTX 4090

24 GB VRAM
29 GB RAM
4 vCPU

Spot

1x GPU $/hr: 0.49
8x GPU $/hr: 3.92

On-Demand

1x GPU $/hr: 0.74
8x GPU $/hr: 5.92

10. L4

24 GB VRAM
GB RAM
vCPU

On-Demand

1x GPU $/hr: 0.44
8x GPU $/hr: 3.52

1 Month

1x GPU $/hr: 0.42
8x GPU $/hr: 3.36

3 Month

1x GPU $/hr: 0.39
8x GPU $/hr: 3.12

6 Month

1x GPU $/hr: 0.37
8x GPU $/hr: 2.96

11. RTX A5000

24 GB VRAM
25 GB RAM
4 vCPU

On-Demand

1x GPU $/hr: 0.44
8x GPU $/hr: 3.52

1 Month

1x GPU $/hr: 0.42
8x GPU $/hr: 3.36

3 Month

1x GPU $/hr: 0.39
8x GPU $/hr: 3.12

6 Month

1x GPU $/hr: 0.37
8x GPU $/hr: 2.96

12. RTX 4000 Ada

20 GB VRAM
31 GB RAM
5 vCPU

On-Demand

1x GPU $/hr: 0.44
8x GPU $/hr: 3.52

13. RTX A4500

20 GB VRAM
29 GB RAM
4 vCPU

Spot

1x GPU $/hr: 0.22
8x GPU $/hr: 1.76

On-Demand

1x GPU $/hr: 0.36
8x GPU $/hr: 2.88

1 Month

1x GPU $/hr: 0.34
8x GPU $/hr: 2.72

3 Month

1x GPU $/hr: 0.32
8x GPU $/hr: 2.56

6 Month

1x GPU $/hr: 0.3
8x GPU $/hr: 2.4

14. RTX A4000

16 GB VRAM
17 GB RAM
2 vCPU

On-Demand

1x GPU $/hr: 0.34
8x GPU $/hr: 2.72

1 Month

1x GPU $/hr: 0.32
8x GPU $/hr: 2.56

3 Month

1x GPU $/hr: 0.3
8x GPU $/hr: 2.4

6 Month

1x GPU $/hr: 0.28
8x GPU $/hr: 2.24

Deploy container-based GPU instances that spin up in seconds using both public and private repositories.

Community Cloud Others

1. A100 80GB

80 GB VRAM
125 GB RAM
8 vCPU

Spot

1x GPU $/hr: 0.89
8x GPU $/hr: 7.12

On-Demand

1x GPU $/hr: 1.69
8x GPU $/hr: 13.52

2. H100 80GB SXM5

80 GB VRAM
251 GB RAM
26 vCPU

Spot

1x GPU $/hr: 2.49
8x GPU $/hr: 19.92

On-Demand

1x GPU $/hr: 4.09
8x GPU $/hr: 32.72

3. H100 80GB PCIe

80 GB VRAM
250 GB RAM
16 vCPU

Spot

1x GPU $/hr: 2.49
8x GPU $/hr: 19.92

On-Demand

1x GPU $/hr: 3.99
8x GPU $/hr: 31.92

4. A40

48 GB VRAM
50 GB RAM
9 vCPU

Spot

1x GPU $/hr: 0.34
8x GPU $/hr: 2.72

On-Demand

1x GPU $/hr: 0.69
8x GPU $/hr: 5.52

5. RTX 6000 Ada

48 GB VRAM
61 GB RAM
8 vCPU

Spot

1x GPU $/hr: 0.69
8x GPU $/hr: 5.52

On-Demand

1x GPU $/hr: 0.99
8x GPU $/hr: 7.92

6. RTX A6000

48 GB VRAM
50 GB RAM
8 vCPU

Spot

1x GPU $/hr: 0.34
8x GPU $/hr: 2.72

On-Demand

1x GPU $/hr: 0.69
8x GPU $/hr: 5.52

7. A30

24 GB VRAM
31 GB RAM
8 vCPU

Spot

1x GPU $/hr: 0.24
8x GPU $/hr: 1.92

On-Demand

1x GPU $/hr: 0.34
8x GPU $/hr: 2.72

8. RTX 3090

24 GB VRAM
27 GB RAM
4 vCPU

Spot

1x GPU $/hr: 0.19
8x GPU $/hr: 1.52

On-Demand

1x GPU $/hr: 0.34
8x GPU $/hr: 2.72

9. RTX 3090 Ti

24 GB VRAM
GB RAM
vCPU

Spot

1x GPU $/hr: 0.2
8x GPU $/hr: 1.6

On-Demand

1x GPU $/hr: 0.36
8x GPU $/hr: 2.88

10. RTX 4090

24 GB VRAM
29 GB RAM
4 vCPU

Spot

1x GPU $/hr: 0.39
8x GPU $/hr: 3.12

On-Demand

1x GPU $/hr: 0.59
8x GPU $/hr: 4.72

Serverless GPUs Others

16 GB A4000: $0.00020

24 GB A5000: $0.00026

24 GB Pro 4090: $0.00044

48 GB A6000: $0.00048

80 GB A100: $0.00130

Features

Autoscale
Bring Container
Logs & Metrics
Multi-GPU
Network Storage
Streaming
Webhooks

Endpoints Custom

Features

Autoscale
Get started quickly
Speech Recognition
Generative Art

Screenshots of Vendor Pricing Page

Disclaimer: The pricing details were last updated on 17/11/2023 from the vendor website and may be different from actual. Please confirm with the vendor website before purchasing.

Learn more about RunPod Pricing.