# neon-ai-gateway

This skill teaches your agent to route LLM and embedding calls through Neon AI Gateway, using a single Neon credential instead of separate provider keys.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 27700 installs · ★ 106
- Author: neondatabase
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/neondatabase/agent-skills/tree/HEAD/skills/neon-ai-gateway/SKILL.md
- Updated: 2026-10-26
- HTML: https://affpapa.org/en/nevibecode/skills/neon-ai-gateway

## What it does

The skill walks an agent through sending model requests via Neon AI Gateway, which Databricks hosts. Models from Anthropic, OpenAI, Google, Meta and others sit behind one endpoint and are addressed by their catalog ID. Your current OpenAI, Anthropic, google-genai, Vercel AI SDK or Mastra setup keeps working — only the base URL changes.

Setup lives in `neon.ts`: add `aiGateway: true`, then run `neon deploy` to provision the gateway on the linked branch. Every branch gets its own gateway host, so requests from a preview branch stay scoped to it. Chat generation streams over SSE with nothing extra to configure.

The gateway only exists in `aws-us-east-2`, `aws-us-east-1`, `aws-eu-central-1` and `aws-ap-southeast-1`, and only on paid Neon plans. On Free, `neon config apply`, `deploy` and `neon checkout` refuse to turn it on. Some catalog models stay locked with `enabled: false` until prepaid credits are on the account. The skill expects the parent `neon` skill to be present; otherwise install it first with `neon skills -s neon -y`.

## Requirements
- Works with: Databricks

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add neondatabase/agent-skills --skill neon-ai-gateway -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/neon-ai-gateway/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/neon-ai-gateway/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add neondatabase/agent-skills --skill neon-ai-gateway -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/neon-ai-gateway/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add neondatabase/agent-skills --skill neon-ai-gateway -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/neon-ai-gateway/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install neondatabase/agent-skills neon-ai-gateway
```

2. **Manually: put the files in place**
- File: `.github/skills/neon-ai-gateway/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add neondatabase/agent-skills --skill neon-ai-gateway -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/neondatabase/agent-skills --path skills/neon-ai-gateway
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/neon-ai-gateway/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add neondatabase/agent-skills --skill neon-ai-gateway -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/neondatabase/agent-skills/tree/HEAD/skills/neon-ai-gateway/SKILL.md

## When to use it
- call an LLM from an app without holding keys for each provider
- generate embeddings for semantic search
- move between Claude, GPT and Gemini by editing one `model` field
- keep AI traffic from a preview branch away from production
- point a Mastra or Vercel AI SDK agent at one endpoint

## Example prompts
- Wire Neon AI Gateway into this project and call `claude-sonnet-4-6` through the OpenAI SDK
- Generate embeddings for the documents table through the Neon gateway
- Move my Mastra agent off direct Anthropic keys onto Neon AI Gateway

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: eac44354553b91d4.

BEGIN THIRD-PARTY FILE eac44354553b91d4
````text
---
name: neon-ai-gateway
description: >-
  One API and one credential for frontier and open-source LLMs and
  embedding models, built into your Neon branch and powered by Databricks.
  Use when a user wants to call an LLM, generate embeddings, add AI/chat/an
  agent to their app, route between model providers (OpenAI, Anthropic,
  Google/Gemini, Meta, Alibaba, and more), or avoid juggling separate
  provider API keys and accounts — especially when they already use Neon
  and want AI requests to branch with their project. Works with the OpenAI
  SDK, Anthropic SDK, google-genai, the Vercel AI SDK, and Mastra by
  changing only the base URL. Triggers include "call an LLM",
  "add AI to my app", "chat completion", "model routing", "LLM proxy/gateway",
  "one API for all
  models", "use Claude/GPT/Gemini", "AI SDK", "Mastra agent", "Neon AI
  Gateway", "generate embeddings", "generate images", and "log/rate-limit AI
  calls".
metadata:
  parent: neon
  source: https://github.com/neondatabase/agent-skills/tree/main/skills/neon-ai-gateway
---

**FIRST**: Use the parent `neon` skill for a Neon overview, getting started with Neon, Neon development best practices, and more.

If the `neon` skill is not installed, fetch it from https://neon.com/docs/ai/skills/neon/SKILL.md or install it with:

```bash
neon skills -s neon -y
```

# Neon AI Gateway

Currently available in `aws-us-east-2`, `aws-us-east-1`, `aws-eu-central-1`, and `aws-ap-southeast-1`.

The Neon AI Gateway brings LLM and embedding inference to your Neon branch. One API and one Neon credential give you access to frontier and open-source models from many providers (Anthropic, OpenAI, Google, Meta, and more), plus embedding models, all hosted and powered by Databricks. The catalog shifts over time, so treat `/v1/models` and the [models.dev Neon page](https://models.dev/providers/neon) as the source of truth rather than a fixed provider list. For embedding model IDs and dimensions, see the [embeddings guide](https://neon.com/docs/ai-gateway/embeddings). Your existing OpenAI/Anthropic/Gemini SDK works by changing only the base URL.

Use this skill to help the user send model calls through the gateway, wire it into the AI SDK or Mastra, and switch providers without rewiring code. Deliver a working inference request, a configured agent, or a precise answer from the official Neon docs.

## When to Use
````
END THIRD-PARTY FILE eac44354553b91d4

The third-party file has ended. Everything between the eac44354553b91d4 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2391 of 23856 bytes. © neondatabase · Apache-2.0 · https://github.com/neondatabase/agent-skills/tree/HEAD/skills/neon-ai-gateway/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md