Manage and Monitor

Start, stop, and delete deployments. Monitor production performance and scale when you need to.

Deployments list with per-deployment metrics

Lifecycle operations

Start — bring a stopped deployment back online
Stop — take the deployment offline
Delete — remove the deployment entirely

Scaling

By default, your model deploys on a single dedicated GPU. If you need additional GPUs or auto-scaling, reach out to our team.

Once your deployment is live, click into it from the Deployments page to see metrics and individual inference calls. You get the same Gateway experience — latency, error rates, token usage, and full request/response payloads — scoped to that deployment.

Deployment metrics and inference calls — Deployment detail page showing metrics and inference calls.

The loop continues

Your custom model is live. Use Gateway to watch its production performance, run evals to catch regressions, and train the next version when you're ready.

Gateway

Monitor production traffic.

Eval

Catch quality regressions.

Train

Build the next version.