Introducing the Vercel AI SDK

This post is historical. Product names and runtime guidance may have changed. For new projects, use with the Node.js runtime and . Use for request-time routing before a response completes.Note:Vercel FunctionsFluid computeRouting Middleware

Over the past 6 months, AI companies like , , , , , and have launched with and Vercel. Vercel helps accelerate your product development by enabling you to focus on creating value with your AI applications, rather than spending time building and maintaining infrastructure.ScaleJasperPerplexityRunwayLexicaJenniNext.js

Today, we're launching new tools to improve the AI experience on Vercel.

The is an library designed to help developers build conversational, streaming, and chat user interfaces in JavaScript and TypeScript. The SDK supports React/Next.js, Svelte/SvelteKit, with support for Nuxt/Vue coming soon.Vercel AI SDKopen-source

To install the SDK, enter the following command in your terminal:

You can also .view the source code on GitHub

Choosing the right LLM for your application is crucial to building a great experience. Each has unique tradeoffs, and can be tuned in different ways to meet your requirements.

Vercel’s AI SDK embraces interoperability, and includes first-class support for , , and Inference. This means that regardless of your preferred AI model provider, you can leverage the Vercel AI SDK to create cutting-edge streaming UI experiences.OpenAILangChainHugging Face

The Vercel AI SDK includes React and Svelte hooks for data fetching and rendering streaming text responses. These hooks enable real-time, dynamic data representation in your application, offering an immersive and interactive experience to your users.

Building a rich chat or completion interface now just takes a few lines of code thanks to and :useChatuseCompletion

We've also included callbacks for storing completed streaming responses to a database within the same request. This feature allows for efficient data management and streamlines the entire process of handling streaming text responses.

The AI SDK works with Vercel Functions. You can deploy AI applications that scale instantly, stream generated responses, and run efficiently with Fluid compute.

With , you write application code in frameworks like Next.js and SvelteKit using the AI SDK, and Vercel converts this code into .framework-defined infrastructureglobal application infrastructure

In late April, we launched an interactive online prompt playground with 20 open source and cloud LLMs.play.vercel.ai

The playground provides a valuable resource for developers to compare various language model results in real-time, tweak parameters, and quickly generate Next.js, Svelte, and Node.js code.

Today, we’ve added a to the playground so you can simultaneously compare chat models side-by-side. We’ve also added code generation support for the Vercel AI SDK. You can now go from playground to chat app in just a few clicks.new chat interface

We'll be adding more in the coming weeks, as well as new templates built entirely with the AI SDK. Further, as new best practices for building applications emerge, we’ll lift them into the SDK based on your feedback.SDK examplesAI

Read more

• **Vercel AI SDK: **Easily stream API responses from AI models

• Explore models from , Hugging Face, and moreChat & Prompt Playground:OpenAI

The Vercel AI SDK

Chat & Prompt Playground

What’s Next?

Built-in LLM Adapters

Streaming First UI Helpers

Stream Helpers and Callbacks

Vercel Functions ready