AI SDK Gateway Provider

Use the AI SDK Gateway provider to access a wide variety of AI models and providers through a unified interface.

What This Skill Does

This skill helps you integrate the AI SDK Gateway provider into your Node.js/TypeScript projects. The Gateway provider allows you to route requests to multiple AI providers (OpenAI, Anthropic, xAI, Google, etc.) using a single consistent API.

Installation

First, install the Gateway provider package:

```bash

npm i @ai-sdk/gateway

```

You'll also need the core AI SDK if not already installed:

```bash

npm i ai

```

Basic Usage

Import and Initialize

```typescript

import { gateway } from '@ai-sdk/gateway';

import { generateText } from 'ai';

```

Generate Text

```typescript

const { text } = await generateText({

model: gateway('xai/grok-3-beta'),

prompt: 'Tell me about the history of the San Francisco Mission-style burrito.',

});

console.log(text);

```

Model Routing

The Gateway provider uses the format `provider/model-name` to route requests:

Advanced Features

Streaming Responses

```typescript

import { streamText } from 'ai';

const { textStream } = await streamText({

model: gateway('anthropic/claude-3-5-sonnet-20241022'),

prompt: 'Write a short story about space exploration.',

});

for await (const chunk of textStream) {

process.stdout.write(chunk);

}

```

Object Generation

```typescript

import { generateObject } from 'ai';

import { z } from 'zod';

const { object } = await generateObject({

model: gateway('openai/gpt-4o'),

schema: z.object({

recipe: z.object({

name: z.string(),

ingredients: z.array(z.string()),

steps: z.array(z.string()),

}),

}),

prompt: 'Generate a recipe for chocolate chip cookies.',

});

console.log(object.recipe);

```

Step-by-Step Implementation

1. **Install dependencies**

```bash

npm i @ai-sdk/gateway ai

```

2. **Import the gateway provider**

```typescript

import { gateway } from '@ai-sdk/gateway';

```

3. **Choose your AI function** (`generateText`, `streamText`, `generateObject`, etc.)

4. **Specify the model** using the `provider/model-name` format

5. **Provide your prompt or schema** and handle the response

6. **Add error handling** for network issues or API failures

Environment Setup

Set up API keys for the providers you'll use:

```bash

.env.local

ANTHROPIC_API_KEY=your_key_here

OPENAI_API_KEY=your_key_here

XAI_API_KEY=your_key_here

```

Common Patterns

Multi-Provider Fallback

```typescript

async function generateWithFallback(prompt: string) {

const models = [

'openai/gpt-4o',

'anthropic/claude-3-5-sonnet-20241022',

'xai/grok-3-beta',

];

for (const model of models) {

try {

return await generateText({ model: gateway(model), prompt });

} catch (error) {

console.error(`Failed with ${model}, trying next...`);

}

}

throw new Error('All providers failed');

}

```

Documentation

For complete documentation, visit [ai-sdk.dev/docs](https://ai-sdk.dev/docs)

Constraints