Netlify AI Gateway Now Supports OpenAI GPT-5.5 Instant With Zero Configuration.

Netlify has added support for OpenAI's GPT-5.5 Instant model to its AI Gateway, allowing developers to integrate advanced language models into their Netlify Functions without manual configuration or credential management.

The update, announced on the Netlify changelog on May 5, enables developers to call the OpenAI SDK directly from any Netlify Function type. The platform handles authentication, caching, and rate limiting automatically, eliminating the need to provision or rotate API keys.

Developers can now use GPT-5.5 Instant by importing the OpenAI SDK and calling the model using the chat-latest API name. The AI Gateway intercepts the request and manages the underlying OpenAI connection transparently.

A basic implementation requires just a few lines of code:

import OpenAI from 'openai';

export default async () => {
  const openai = new OpenAI();
  const response = await openai.responses.create({
    model: 'chat-latest',
    input: 'How does AI work?'
  });
  return Response.json(response);
};

The approach reduces friction for teams building AI features into web applications. No environment variables, no credential rotation workflows, no separate infrastructure to provision.

Netlify's AI Gateway sits between developer code and external AI providers. When a Function makes an OpenAI request, the gateway automatically applies caching to reduce redundant API calls, enforces rate limits to prevent quota exhaustion, and authenticates requests using Netlify's internal systems.

This architecture matters for teams managing multiple projects or agents that generate code. As previously covered, Netlify has been positioning itself as a deployment platform for AI-generated applications, where automated tools might spin up hundreds of sites without human oversight of every API key.

The gateway model also allows Netlify to swap underlying providers or negotiate bulk pricing without requiring developers to change their code.

GPT-5.5 Instant support extends across Netlify's entire function infrastructure: serverless functions, background functions, and edge functions all work with the same API. This means developers can choose the right execution model for their use case, whether that's sub-100ms edge responses or longer-running background processing, without rewriting AI integration code.

The feature is live now for all Netlify users. Full documentation is available in the AI Gateway overview.