Quick StartQuick Start

Get Started

AI Gateway offers a unified API to multiple providers with budgets, monitoring, load-balancing, and fallbacks. Choose a quickstart based on what you want to build.

AI Assistance

Set up AI Gateway for text generation. First, make sure the Vercel CLI is installed (`npm i -g vercel`). If I'm using Claude Code, Codex, or Cursor, install the Vercel Plugin (`npx plugins add vercel/vercel-plugin`). For other agents, install Vercel Skills (`npx skills add vercel-labs/agent-skills`). Then: 1. Initialize a Node.js project and install the `ai` package, dotenv, @types/node, tsx, and typescript. 2. Save my AI_GATEWAY_API_KEY in .env.local. 3. Create an index.ts that uses the AI SDK streamText function with the model 'openai/gpt-5.4' to stream a response and log token usage. 4. Run it with tsx to verify it works.

1

Set up your project

Create a new directory and initialize a Node.js project.

mkdir ai-text-demo && cd ai-text-demo
pnpm init

2

Install dependencies

Install the AI SDK and development dependencies.

pnpm add ai dotenv @types/node tsx typescript

3

Set up your API key

Create an API key in your Vercel dashboard and save it to your environment file.

AI_GATEWAY_API_KEY=your_api_key_here

Alternatively, use OIDC tokens for automatic authentication in Vercel deployments.

4

Create and run your script

Save this script as index.ts and run it with tsx.

import { streamText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = streamText({
    model: 'openai/gpt-5.4',
    prompt: 'Invent a new holiday and describe its traditions.',
  });

  for await (const textPart of result.textStream) {
    process.stdout.write(textPart);
  }

  console.log();
  console.log('Token usage:', await result.usage);
}

main().catch(console.error);

pnpm tsx index.ts

Next steps: Learn about provider routing, OpenAI compatibility, or try other SDKs like Anthropic.

Learn more about AI Gateway features including OpenAI compatibility, provider routing, and bring your own keys (BYOK).

Get Started

AI Gateway offers a unified API to multiple providers with budgets, monitoring, load-balancing, and fallbacks. Choose a quickstart based on what you want to build.

AI Assistance

Set up AI Gateway for text generation. First, make sure the Vercel CLI is installed (`npm i -g vercel`). If I'm using Claude Code, Codex, or Cursor, install the Vercel Plugin (`npx plugins add vercel/vercel-plugin`). For other agents, install Vercel Skills (`npx skills add vercel-labs/agent-skills`). Then: 1. Initialize a Node.js project and install the `ai` package, dotenv, @types/node, tsx, and typescript. 2. Save my AI_GATEWAY_API_KEY in .env.local. 3. Create an index.ts that uses the AI SDK streamText function with the model 'openai/gpt-5.4' to stream a response and log token usage. 4. Run it with tsx to verify it works.

1

Set up your project

Create a new directory and initialize a Node.js project.

mkdir ai-text-demo && cd ai-text-demo
pnpm init

2

Install dependencies

Install the AI SDK and development dependencies.

pnpm add ai dotenv @types/node tsx typescript

3

Set up your API key

Create an API key in your Vercel dashboard and save it to your environment file.

AI_GATEWAY_API_KEY=your_api_key_here

Alternatively, use OIDC tokens for automatic authentication in Vercel deployments.

4

Create and run your script

Save this script as index.ts and run it with tsx.

import { streamText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = streamText({
    model: 'openai/gpt-5.4',
    prompt: 'Invent a new holiday and describe its traditions.',
  });

  for await (const textPart of result.textStream) {
    process.stdout.write(textPart);
  }

  console.log();
  console.log('Token usage:', await result.usage);
}

main().catch(console.error);