AI SDK - Perplexity Provider

The Perplexity provider for the AI SDK contains language model support for Perplexity's Agent API, including web search, citations, function tools, and structured output.

Features

• Real-time web search grounding for accurate, up-to-date responses
• Agent API presets from fast through xhigh
• Direct access to supported third-party models through Perplexity
• Native tools for web search, URL fetching, code execution, finance, MCP, and connectors
• AI SDK function tools, structured output, reasoning streams, and multi-turn tool calls

Deploying to Vercel? With Vercel's AI Gateway you can access Perplexity (and hundreds of models from other providers) — no additional packages, API keys, or extra cost. Get started with AI Gateway.

Setup

The Perplexity provider is available in the @ai-sdk/perplexity module. You can install it with:

npm i @ai-sdk/perplexity

Skill for Coding Agents

If you use coding agents such as Claude Code or Cursor, we highly recommend adding the AI SDK skill to your repository:

npx skills add vercel/ai

Provider Instance

You can import the default provider instance perplexity from @ai-sdk/perplexity:

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

Example

import { perplexity } from '@ai-sdk/perplexity';
import { generateText } from 'ai';

const { text } = await generateText({
  model: perplexity('low'),
  prompt: 'What are the latest developments in quantum computing?',
});

Version 5 is a breaking migration from Sonar Chat Completions to the Agent API. Legacy Sonar model IDs and provider options are not mapped. Review the migration notes before upgrading an existing application.

Perplexity supports Sonar Chat Completions only until September 27, 2026. Remaining on version 4 will not preserve language generation after that date. Migrate unsupported Sonar features using the alternatives in the migration notes.

Documentation

Please check out the Perplexity provider documentation for more information.