Pricing

Pricing

Fast, reliable, and cost-efficient.

fal.ai adapts to your usage, ensuring you only pay for the computing power you consume. It's cost-effective scalability at its best.

For private serverless model pricing, please see our enterprise pricing page.

Competitive pricing for custom deployments. Get H100s from from as low as $1.99/hr. Contact support, support@fal.ai, to get started.

GPU H100 icon
GPUH100
VRAM80GB
Price per hour*$1.99/h
Price per second*$0.0006/s
GPU H200 icon
GPUH200
VRAM141GB
Price per hour*$2.10/h
Price per second*$0.0006/s
GPU A100 icon
GPUA100
VRAM40GB
Price per hour*$0.99/h
Price per second*$0.0003/s
GPU A6000 icon
GPUA6000
VRAM48GB
Price per hour*$0.60/h
Price per second*$0.0002/s
GPU GPU-B200 icon
GPUGPU-B200
VRAM192GB
Price per hour*contact us
Price per second*contact us

*starting at

Billing Based on Model Output

The models below are billed by model output, instead of compute seconds.
Model NameUnit Price (USD)