netlify-ai-gateway
Guide for using Netlify AI Gateway to access AI models. Use when adding AI capabilities or selecting/changing AI models. Must be read before choosing a model. Covers supported providers (OpenAI, Anthropic, Google), SDK setup, environment variables, and the list of available models.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-01
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- netlify-ai-gateway
- description
- Guide for using Netlify AI Gateway to access AI models. Use when adding AI capabilities or selecting/changing AI models. Must be read before choosing a model. Covers supported providers (OpenAI, Anthropic, Google), SDK setup, environment variables, and the list of available models.
02 资源文件 4
- 参考文档agents/openai.yaml336 B
- 资产文件assets/netlify-small.svg1.3 KB
- 资产文件assets/netlify.png2.6 KB
- 许可证LICENSE.txt10.5 KB
03 SKILL.md 正文
Netlify AI Gateway
IMPORTANT: Only use models listed in the "Available Models" section below. AI Gateway does not support every model a provider offers. Using an unsupported model will cause runtime errors.
Netlify AI Gateway provides access to AI models from multiple providers without managing API keys directly. It is available on all Netlify sites.
How It Works
The AI Gateway acts as a proxy — you use standard provider SDKs (OpenAI, Anthropic, Google) but point them at Netlify's gateway URL instead of the provider's API. Netlify handles authentication, rate limiting, and monitoring.
Setup
- Enable AI on your site in the Netlify UI
- The environment variable
OPENAI_BASE_URLis set automatically by Netlify - Install the provider SDK you want to use
No provider API keys are needed — Netlify's gateway handles authentication.
Using OpenAI SDK
npm install openai
import OpenAI from "openai";
const openai = new OpenAI();
// OPENAI_BASE_URL is auto-configured — no API key or base URL needed
const completion = await openai.chat.completions.create({
model: "gpt-4o-mini",
messages: [{ role: "user", content: "Hello!" }],
});
Using Anthropic SDK
npm install @anthropic-ai/sdk
import Anthropic from "@anthropic-ai/sdk";
const client = new Anthropic({
baseURL: Netlify.env.get("ANTHROPIC_BASE_URL"),
});
const message = await client.messages.create({
model: "claude-sonnet-4-5-20250929",
max_tokens: 1024,
messages: [{ role: "user", content: "Hello!" }],
});
Using Google AI SDK
npm install @google/generative-ai
import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI("placeholder");
// Configure base URL via environment variable
const model = genAI.getGenerativeModel({ model: "gemini-2.5-flash" });
const result = await model.generateContent("Hello!");
In a Netlify Function
import type { Config, Context } from "@netlify/functions";
import OpenAI from "openai";
export default async (req: Request, context: Context) => {
const { prompt } = await req.json();
const openai = new OpenAI();
const completion = await openai.chat.completions.create({
model: "gpt-4o-mini",
messages: [{ role: "user", content: prompt }],
});
return Response.json({
response: completion.choices[0].message.content,
});
};
export const config: Config = {
path: "/api/ai",
method: "POST",
};
Environment Variables
| Variable | Provider | Set by |
|---|---|---|
OPENAI_BASE_URL |
OpenAI | Netlify (automatic) |
ANTHROPIC_BASE_URL |
Anthropic | Netlify (automatic) |
These are configured automatically when AI is enabled on the site. No manual setup required.
Local Development
With @netlify/vite-plugin or netlify dev, gateway environment variables are injected automatically. The AI Gateway is accessible during local development after the site has been deployed at least once.
Available Models
For the list of supported models, see https://docs.netlify.com/build/ai-gateway/overview/.
04 同仓库更多 Skills
yeet
Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).
yayin-seo-geo-yasal-denetim
Bir web uygulaması canlıya çıkmadan veya iş teslimi biterken resmî/kurumsal sayfaları, SEO, GEO, indeksleme ve canlı çıktıyı denetler; eksikleri kodda tamamlar ve üretimde kanıtlar. Uygulama bitti, canlıya hazır mı, yayına al, launch checklist, release readiness, SEO audit, GEO audit, legal pages, privacy policy, terms, cookies, KVKK, robots, sitemap, canonical, hreflang, JSON-LD, llms.txt ifadelerinde kullan. Yeni veya önemli ölçüde değişmiş halka açık web uygulamasının son teslim aşamasında kullanıcı ayrıca istemese de uygula. Güvenlik sızma testi için güvenlik skillini ayrıca kullan.
xurl
X/Twitter via xurl CLI: post, search, DM, media, v2 API.
wrangler
Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
winui-app
Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and CommunityToolkit components. Use when creating a brand new app, preparing a machine for WinUI, reviewing, refactoring, planning, troubleshooting, environment-checking, or setting up WinUI 3 XAML, controls, navigation, windowing, theming, accessibility, responsiveness, performance, deployment, or related Windows app design and development work.
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.