Come and meet us at the MLOps Summit in San Francisco on the 15th and 16th of June!
Join us!

The API for
Machine Learning

The bridge between engineering and ML has never been shorter
Get started

Introducing

Production-ready ML models for inference.

From standard language tasks to image processing, our model hub hosts a range of popular models to power your next ML app.

.py

Copy

1

2

3

4

5

6

7

8

9

from pipeline import PipelineCloud

api
= PipelineCloud("YOUR_API_TOKEN")

# GPT-J Pipeline
model_id = "pipeline_d7502b78863744c495d7d22f321cf7ff"                          
query = "What is the distance between London and NYC?"

run
= api.run_pipeline(model_id, query)

Start your free trial

Join over 2,500+ data engineers already using Pipeline Model Hub.

Access Model Hub

Why use Pipeline?

Serverless GPU for all your ML

We are here to make ML infrastructure easy

Instant infrastructure

Launch inference or training on cloud GPUs in the blink of an eye. Smart scaling will support your usage as it grows.

Fast and optimised API

Automatically get endpoints for any model or pipeline. You do the data science, our compute engine does the heavy lifting.

Serverless pricing

No quotas, no minimums, no hourly rental. We charge only for the milliseconds of GPU use your workload needs to complete.

Support from ML enthusiasts

Our team are knowledgeable and friendly. They’ll help you import models and maximise their performance. All within 24 hours, guaranteed.

Pricing

Pricing for our Cloud

A single pricing for Pipeline Model Hub and all other Pipeline products.
Start for free
Start using our API with 10h in free credit and a 1 month free account access.
Pay only for compute usage
Create an account and pay per millisecond of compute usage, only pay for the time the GPU processes your request.
Fast and scalable API
Instantly plug any of our ML models into your service.

Developer account

$2 per GPU hour

($0.00000056 per ms)

+ Account access

$12.99/month

Looking for more?

Model fine-tuning

Custom pipelines for your use-case

24/7 direct support

Contact us
Coming soon...

Keep track of your ML pipelines and deploy everywhere.

Learn more