everpod 0.1.0

Python client for Everpod — GPU inference on Household AI Infrastructure

everpod

Python client for Everpod — GPU inference on Household AI Infrastructure.

pip install everpod

from everpod import Everpod

client = Everpod(api_key="evp_...")  # or set EVERPOD_API_KEY

image = client.images.generate(prompt="a lighthouse at dusk, cinematic")
image.save("lighthouse.png")

Generation runs as a job on a real GPU node; generate() polls to completion for you. For async control:

job = client.images.submit(prompt="a lighthouse at dusk")
job = client.jobs.wait(job.id, timeout=120)
print(job.artifacts[0].url)

Check live capacity before submitting — models are only offered while a node can serve them:

for model in client.models.available():
    print(model.name, model.ready_workers)

Your metered usage (nothing is billed during the pilot):

usage = client.usage.get(days=30)
print(usage.total_jobs, usage.total_gpu_seconds)
for row in usage.recent:
    print(row["job_id"], row["gpu_seconds"])

Get an API key at app.everpod.io/keys · API reference at api.everpod.io/docs.