LaunchDevelopersNovember 16, 2026

Vercel AI Gateway adds Private Inference for custom model endpoints

Read original source →vercel.com

Private Inference routes fine-tuned, self-hosted, or prerelease models through the same auth, SDKs, and observability as catalog models, so switching only changes the model ID. Private models stay scoped to your Vercel team, aren't listed publicly, and credentials are stored encrypted with optional Zero Data Retention.

1 source

More stories today

Open the live feed