ProductsNov 16, 2026, 2:47 AM EST

Vercel adds Private Inference to AI Gateway for custom model endpoints

Vercel's AI Gateway now supports Private Inference, which lets teams connect their own model endpoints — fine-tuned, self-hosted, or prerelease models — and run them through the same authentication, SDKs, APIs, and observability as catalog models. Requests can be made through Chat Completions, Responses, or Messages, with the Gateway translating each one to the endpoint's format so switching models only changes the model ID.

Private models are scoped to the owning Vercel team and are not listed in the public catalog. Credentials are stored encrypted, Zero Data Retention can be enabled per provider, and teams may optionally fall back to a catalog model if a private endpoint fails. Private models can be used in coding agents like Claude Code, Codex, and Cursor, and their traffic appears in logs alongside catalog requests. Setup is through the Private Inference page or Vercel CLI 65.16.0 or later, calling models by a private/<slug> ID.

Why it matters

Teams running their own or prerelease models no longer need separate keys, client code, and logs for them: those models can now be tracked, secured, and failed over in the same place as off-the-shelf ones.

Sources

Written by AIToolMaps from the source above and checked against it sentence by sentence.

Comments

No comments yet