# AI Gateway now supports Private Inference

Source: [Vercel](https://vercel.com/changelog/ai-gateway-now-supports-private-inference)  
Feed7 permalink: https://feed7.dev/p/ai-gateway-now-supports-private-inference-0gm4r3j  
Published: 2026-11-16T07:47:00.000Z  
Trust: Official Source (official_source)

## Why Included

AI Gateway can route private model endpoints through the same APIs, agent connections, logs, and reporting as catalog models, with optional catalog-model fallback.

## Source Summary

Private Inference connects self-hosted, fine-tuned, or prerelease model endpoints to AI Gateway. Private models use the same authentication, SDKs, and APIs as catalog models; requests appear in shared logs and reporting. **Vercel CLI 65.16.0 or later** can register providers and models.
If you run a private model behind a coding agent, this can consolidate its credentials, calls, and observability with catalog-model traffic. The gateway translates supported request formats, so switching models can be a model-ID change; an optional catalog-model fallback is available.
Private models are scoped to your Vercel team and excluded from the public catalog. Check the documentation for supported model types, requirements, and billing details before connecting an endpoint.

## Practical Implication

No separate implication recorded.

## Agent-Ready Context

Private Inference connects self-hosted, fine-tuned, or prerelease model endpoints to AI Gateway. Private models use the same authentication, SDKs, and APIs as catalog models; requests appear in shared logs and reporting. **Vercel CLI 65.16.0 or later** can register providers and models.
If you run a private model behind a coding agent, this can consolidate its credentials, calls, and observability with catalog-model traffic. The gateway translates supported request formats, so switching models can be a model-ID change; an optional catalog-model fallback is available.
Private models are scoped to your Vercel team and excluded from the public catalog. Check the documentation for supported model types, requirements, and billing details before connecting an endpoint.

## Connected Context

Feed7 judgment across 1116 accumulated Signals:

Private Inference extends AI Gateway’s shared authentication, APIs, logs, and reporting to team-scoped private endpoints, with optional catalog fallback. This makes gateway-based agent setups usable for private or prerelease models while preserving common observability. The CLI version requirement and endpoint compatibility checks are practical prerequisites before connecting one.

- [Set up coding agents in one command with AI Gateway](https://feed7.dev/p/set-up-coding-agents-in-one-command-with-ai-gateway-0wmcqce) — The setup command centralizes gateway configuration across coding-agent clients; Private Inference extends that same gateway path to private model endpoints.
- [AI Gateway logs now have a dedicated page](https://feed7.dev/p/ai-gateway-logs-1272t5j) — Private-model calls appearing in shared reporting make the dedicated request logs relevant for inspecting their cost, latency, routing, and fallback behavior.
- [Virtual models now available on AI Gateway](https://feed7.dev/p/virtual-models-now-available-on-ai-gateway-1nnw9v7) — Virtual Models centralize model settings and routing under stable task IDs; Private Inference supplies private endpoints as another model source that gateway configuration can manage.

## Context Map

- Layer: infra
- Domains: coding
- Topics: coding-agents, gateways, observability

## Uncertainty

- None recorded.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.
