On-demand price is $0.00015 / step.
Get more details

And use it in the following codes.

import os
from leptonai.client import Client

api_token = os.environ.get('LEPTON_API_TOKEN')
c = Client("https://sdxl.lepton.run", token=api_token)

image = c.run(
    prompt="Astronaut on Mars During sunset",
    height=1024,
    width=1024,
    guidance_scale=5,
    high_noise_frac=0.75,
    seed=1809774958,
    steps=30,
    use_refiner=False
)
with open('output_image.png', 'wb') as f:
    f.write(image)
print("Image saved as output_image.png")

The rate limit for the Serverless Endpoints is 10 requests per minute across all models under Basic Plan. If you need a higher rate limit with SLA please upgrade to standard plan, or use dedicated deployment.

Lepton AI

© 2024