Enterprise

Serverless GPU inference for ML models

We're offering $50 free compute for all users

Get started — it's free
import os
from pipeline.cloud.pipelines import run_pipeline

os.environ["PIPELINE_API_TOKEN"] = "YOUR_TOKEN"

output = run_pipeline(
	#pipeline pointer or ID
	"stabilityai/stable-diffusion-xl-refiner-1.0:v1",
	#:Prompt
	"a cool dog, holding a coffee wearing a comfy hoodie",
	#:Model kwargs
	dict(
		denoising_end = 0.8,
		num_inference_steps = 25,
	),
	async_run = False,
)

print(output.result.result_array())
  • Cheaper than AWS or GCP

    Reduced GPU usage with serverless.

  • Up-to-date enterprise hardware

    NVIDIA Ampere and Volta GPUs.

  • Save engineering time

    We handle the cloud infrastructure as you scale.

  • Unlimited requests

    No changes required as your product grows.

  • Reduced cold start

    Low latency and reliable response times.

  • Rapid support

    Personal specialist help.

New
Public models

State-of-the-art AI models, one API call away.

Explore some of our most popular pre-trained AI models available as an API.

somename/test

some description goes here

Uploaded 2

4444

somename/test

some description goes here

Uploaded 2

4444

somename/test

some description goes here

Uploaded 2

4444

somename/test

some description goes here

Uploaded 2

4444

somename/test

some description goes here

Uploaded 2

4444

somename/test

some description goes here

Uploaded 2

4444

somename/test

some description goes here

Uploaded 2

4444

somename/test

some description goes here

Uploaded 2

4444

Explore more models
Alpha
Custom models

Deploy your own private or public ML models

Upload your model and instantly get an inference API endpoint.

With our open source library, you can convert your model to a pipeline and get access to our API within minutes.

Contact us

Currently, Catalyst deploy is on request

Start your AI journey today

Join over 4,500+ customers already using Pipeline Catalyst