> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/vercel/ai/llms.txt
> Use this file to discover all available pages before exploring further.

# AI SDK by Vercel

> The TypeScript toolkit for building AI applications and agents with React, Next.js, Vue, Svelte, Node.js, and more.

# AI SDK by Vercel

The AI SDK is the TypeScript toolkit designed to help developers build AI-powered applications and agents with React, Next.js, Vue, Svelte, Node.js, and more.

<CardGroup cols={2}>
  <Card title="Installation" icon="download" href="/installation">
    Get started by installing the AI SDK in your project
  </Card>

  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Build your first AI application in minutes
  </Card>

  <Card title="AI SDK Core" icon="code" href="/ai-sdk-core">
    Generate text, structured objects, and build agents with LLMs
  </Card>

  <Card title="AI SDK UI" icon="browser" href="/ai-sdk-ui">
    Framework-agnostic hooks for chat and generative interfaces
  </Card>
</CardGroup>

## Why use the AI SDK?

Integrating large language models (LLMs) into applications is complicated and heavily dependent on the specific model provider you use.

The AI SDK standardizes integrating artificial intelligence (AI) models across supported providers. This enables developers to focus on building great AI applications, not waste time on technical details.

### Unified API across providers

Switch between different AI providers with minimal code changes. The AI SDK provides a consistent interface whether you're using OpenAI, Anthropic, Google, or other providers:

```typescript theme={null}
import { generateText } from 'ai';
import { openai } from '@ai-sdk/openai';
import { anthropic } from '@ai-sdk/anthropic';

// Use OpenAI
const result1 = await generateText({
  model: openai('gpt-4o'),
  prompt: 'What is an agent?',
});

// Switch to Anthropic with the same code structure
const result2 = await generateText({
  model: anthropic('claude-sonnet-4-5'),
  prompt: 'What is an agent?',
});
```

### Or use Vercel AI Gateway

The Vercel AI Gateway provides instant access to all major providers with a single API key:

```typescript theme={null}
import { generateText } from 'ai';

// Access any model with a simple string
const result = await generateText({
  model: 'openai/gpt-4o',
  prompt: 'What is an agent?',
});
```

## Core capabilities

The AI SDK has two main libraries:

<CardGroup cols={2}>
  <Card title="AI SDK Core" icon="code">
    A unified API for generating text, structured objects, tool calls, and building agents with LLMs.
  </Card>

  <Card title="AI SDK UI" icon="browser">
    Framework-agnostic hooks for quickly building chat and generative user interfaces.
  </Card>
</CardGroup>

### Generate text

Generate text completions with streaming support:

```typescript theme={null}
import { generateText } from 'ai';
import { openai } from '@ai-sdk/openai';

const { text } = await generateText({
  model: openai('gpt-4o'),
  prompt: 'What is an agent?',
});
```

### Generate structured data

Generate type-safe structured outputs using Zod schemas:

```typescript theme={null}
import { generateText, Output } from 'ai';
import { openai } from '@ai-sdk/openai';
import { z } from 'zod';

const { output } = await generateText({
  model: openai('gpt-4o'),
  output: Output.object({
    schema: z.object({
      recipe: z.object({
        name: z.string(),
        ingredients: z.array(
          z.object({ name: z.string(), amount: z.string() })
        ),
        steps: z.array(z.string()),
      }),
    }),
  }),
  prompt: 'Generate a lasagna recipe.',
});
```

### Build agents with tools

Create agents that can use tools to accomplish tasks:

```typescript theme={null}
import { generateText, tool } from 'ai';
import { openai } from '@ai-sdk/openai';
import { z } from 'zod';

const result = await generateText({
  model: openai('gpt-4o'),
  tools: {
    weather: tool({
      inputSchema: z.object({
        location: z.string(),
      }),
      execute: async ({ location }) => {
        // Call weather API
        return { temperature: 72, condition: 'sunny' };
      },
    }),
  },
  prompt: 'What is the weather in San Francisco?',
});
```

### Stream text and UI

Stream responses for real-time user interfaces:

```typescript theme={null}
import { streamText } from 'ai';
import { openai } from '@ai-sdk/openai';

const result = streamText({
  model: openai('gpt-4o'),
  prompt: 'Invent a new holiday and describe its traditions.',
});

for await (const chunk of result.textStream) {
  console.log(chunk);
}
```

## Supported providers

The AI SDK supports multiple model providers out of the box:

<CardGroup cols={3}>
  <Card title="OpenAI" icon="openai">
    GPT-4o, GPT-4, GPT-3.5 Turbo
  </Card>

  <Card title="Anthropic" icon="anthropic">
    Claude 4.5, Claude 3.5 Sonnet
  </Card>

  <Card title="Google" icon="google">
    Gemini 2.5 Flash, Gemini Pro
  </Card>

  <Card title="Mistral" icon="mistral">
    Mistral Large, Mistral Medium
  </Card>

  <Card title="Meta" icon="meta">
    Llama 3.3, Llama 3.1
  </Card>

  <Card title="And more" icon="ellipsis">
    Amazon Bedrock, Azure, Cohere, and custom providers
  </Card>
</CardGroup>

## Framework integrations

Build AI applications with your favorite framework:

<CardGroup cols={2}>
  <Card title="Next.js" icon="nextjs">
    React Server Components and App Router support
  </Card>

  <Card title="React" icon="react">
    Hooks for building chat interfaces
  </Card>

  <Card title="Vue" icon="vue">
    Composables for Vue 3 applications
  </Card>

  <Card title="Svelte" icon="svelte">
    Stores and utilities for Svelte apps
  </Card>

  <Card title="Node.js" icon="node">
    Express, Fastify, and native HTTP support
  </Card>

  <Card title="Angular" icon="angular">
    Services for Angular applications
  </Card>
</CardGroup>

## Next steps

<CardGroup cols={2}>
  <Card title="Install the SDK" icon="download" href="/installation">
    Set up the AI SDK in your project
  </Card>

  <Card title="Build your first app" icon="rocket" href="/quickstart">
    Follow the quickstart guide
  </Card>

  <Card title="Explore providers" icon="server" href="/providers">
    Learn about available AI providers
  </Card>

  <Card title="API reference" icon="book" href="/reference">
    Dive into the complete API documentation
  </Card>
</CardGroup>

## Join our community

If you have questions about anything related to the AI SDK, you're always welcome to ask our community on [the Vercel Community](https://community.vercel.com/c/ai-sdk/62).