Pricing That Scales With You.

RunGen.AI is free to use, and you just pay when you run a model.

Llama-3.1-8B
Starting at
$ 0.02/min
DeepSeek-R1-Distill-Llama-8B
Starting at
$ 0.02/min
FLUX.1-dev
Starting at
$ 0.04/min
s1-32b
Starting at
$0.09/min
phi-3 mini
Starting at
$0.02/min
Mistral-7B
Starting at
$ 0.02/min
gemma-7b
Starting at
$ 0.02/min

Check price for your favorite model

Stable pricing for your workloads.

You can control how much power you need. RunGen.AI prices your models hourly, automatically determining which tiers are available with your model. And should you ever need more power, you can seamlessly upgrade – without downtime.

Basic

¢2

/minute

For lightweight usage

min. 6vCPU, 24GB VRAM

Best for experimentation

Basic

¢2

/minute

For lightweight usage

min. 6vCPU, 24GB VRAM

Best for experimentation

Standard

¢4

/minute

Balance cost vs. performance

min. 8 vCPU, 48GB VRAM

Enhanced performance for production workloads

Standard

¢4

/minute

Balance cost vs. performance

min. 8 vCPU, 48GB VRAM

Enhanced performance for production workloads

Standard

¢4

/minute

Balance cost vs. performance

min. 8 vCPU, 48GB VRAM

Enhanced performance for production workloads

Performance

¢9

/minute

For serious workloads

min. 14 vCPU, 80GB VRAM

Supports big models

Performance

¢9

/minute

For serious workloads

min. 14 vCPU, 80GB VRAM

Supports big models

Performance

¢9

/minute

For serious workloads

min. 14 vCPU, 80GB VRAM

Supports big models

Or contact us for enterprise offers – [email protected]

Deploy to Production in Minutes

Get Started

Deploy to Production in Minutes

Get Started

Deploy to Production in Minutes

Get Started