# Serve existing ML models beside your data: plan the endpoint

Predict serves classic ML models and records predictions with your data systems. Evaluate compatibility, feature freshness and operational behavior before moving an existing endpoint.

## Relevant capabilities

- Serving for supported classic ML model formats
- dbt feature models and prediction logs in ClickHouse
- Data-quality monitors

## How to compare

- Is the trained model and its runtime supported?
- How will online features match the training definitions?
- What latency, availability and rollback requirements apply?

## Bring these inputs

- Model artifact and runtime requirements
- Feature definitions and reference predictions
- Traffic and monitoring requirements

## A practical first workflow

- Confirm compatibility for one existing model.
- Compare reference predictions and feature inputs in a pilot.
- Exercise rollout, monitoring and rollback before cutover.

## Check before expanding

- Check prediction equivalence on reference cases.
- Measure feature freshness and serving latency.
- Validate logging, drift review and rollback ownership.

## Economics
Compare the cloud bill, platform charges, operating effort and migration work for the same workload. Cloud capacity is not free. Charges and scope need agreement before paid deployment.

## Switching considerations
AWS and Google Cloud are available today; other deployment environments are roadmap. Preserve the existing workload and access path until compatibility, recovery and cutover checks pass.

## Free next step
Get a free deployment checklist, then create your workspace. Free expert help with your use case is also available through our contact form.

[Create your HyperLake workspace](https://app.hyperlake.cloud/users/sign_in?intent=classic-ml-serving&offer_id=starter-checklist-v1&utm_source=hyperlake&utm_medium=owned&utm_campaign=signup-journey&utm_content=landing_hero)

[Download the free checklist](https://hyperlake.cloud/solutions/classic-ml-serving.txt)

No free cloud capacity is promised. Deployment scope and charges are agreed separately; AWS and Google Cloud are available today.

## Sources
- https://hyperlake.cloud/stacks
- https://hyperlake.cloud/faq
- https://hyperlake.cloud/get-started

[Discuss this workload](https://hyperlake.cloud/contact)