# AI Gateway now supports Private Inference

> Source: <https://vercel.com/changelog/ai-gateway-now-supports-private-inference>
> Published: 2026-11-16 07:47:00+00:00

**Key takeaway:** Private models are called with a `private/<slug>` model ID through Chat Completions, Responses or Messages, and registering a provider requires Vercel CLI 65.16.0 or later.

[Private Inference](https://vercel.com/docs/ai-gateway/security-and-compliance/private-inference) connects your own model endpoints to [AI Gateway](https://vercel.com/ai-gateway).

Enterprises running fine-tuned, self-hosted, or prerelease models used to need separate keys, client code, and logs for them. Those models can now run through the same authentication, [SDKs and APIs](https://vercel.com/docs/ai-gateway/sdks-and-apis), and observability as [catalog models](https://vercel.com/ai-gateway/models), so every model your team uses is managed in one place.

Use Private Inference to:

**Switch between private and catalog models:** Call private models through Chat Completions, Responses, or Messages. AI Gateway translates each request to your endpoint's format, so switching only changes the model ID.

**Keep models scoped to your team:** Only your Vercel team can view or call private models, and they aren't listed in the public catalog. Credentials are stored encrypted, and you can enable [Zero Data Retention](https://vercel.com/docs/ai-gateway/security-and-compliance/zdr) per provider.

**Connect coding agents:** Use private models in Claude Code, Codex, Cursor, and other [coding agents](https://vercel.com/docs/ai-gateway/coding-agents) connected to AI Gateway.

**Monitor traffic together:** View private model requests alongside catalog traffic in [logs](https://vercel.com/docs/ai-gateway/observability-and-spend/logs), [trace drains](https://vercel.com/docs/ai-gateway/observability-and-spend/trace-drains), and [custom reporting](https://vercel.com/docs/ai-gateway/observability-and-spend/custom-reporting). [Observability](https://vercel.com/docs/ai-gateway/observability-and-spend/observability) charts break down requests, tokens, and time to first token by private model.

**Configure fallbacks:** Optionally [fall back to a catalog model](https://vercel.com/docs/ai-gateway/models-and-providers/model-fallbacks) if your private endpoint fails.

To get started, open the [Private Inference page](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai-gateway%2Fprivate-inference&title=AI+Gateway+Private+Inference) and add your endpoint as a private provider. Enter its base URL, select its API format, and add its credentials. Then add the models it serves.

You can also register the provider and model with the [Vercel CLI](https://vercel.com/docs/cli/ai-gateway), version 65.16.0 or later:

Call the model using its `private/<slug>` ID:

Private model requests appear in [AI Gateway logs](https://vercel.com/docs/ai-gateway/observability-and-spend/logs) alongside requests to catalog models.

type: embedded-entry-inline id: 1GzjEiRrj3NaTriLhtBYIX

Read the [Private Inference documentation](https://vercel.com/docs/ai-gateway/security-and-compliance/private-inference) for supported model types, requirements, and billing details.
