Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

The Vercel AI SDK is a TypeScript-first toolkit for building AI-powered apps with a unified provider interface, streaming primitives, and React hooks. The official @ai-sdk/perplexity provider gives you full access to Perplexity’s Sonar models — including streaming, citations, image results, and PDF inputs — with a one-line model identifier.
Vercel AI SDK powers generateText, streamText, generateObject, and React hooks like useChat and useCompletion. Learn more at ai-sdk.dev.

​
Installation

pnpm add @ai-sdk/perplexity ai

​
API Key Setup

Set your Perplexity API key: 
export PERPLEXITY_API_KEY="your_api_key_here"

Get API Key

Generate your Perplexity API key from the API portal.

​
Quick Start

Import the default provider instance and call generateText: 
import { perplexity } from "@ai-sdk/perplexity";
import { generateText } from "ai";

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

console.log(text);

​
Accessing Citations

Every response includes a sources array of the URLs Perplexity consulted: 
import { perplexity } from "@ai-sdk/perplexity";
import { generateText } from "ai";

const { text, sources } = await generateText({
  model: perplexity("sonar-pro"),
  prompt: "What are the latest developments in quantum computing?",
});

console.log(text);
console.log(sources);

​
Provider Options

Pass Perplexity-specific parameters through providerOptions.perplexity: 
import { perplexity } from "@ai-sdk/perplexity";
import { generateText } from "ai";

const result = await generateText({
  model: perplexity("sonar-pro"),
  prompt: "What are the latest developments in quantum computing?",
  providerOptions: {
    perplexity: {
      return_images: true,
      search_recency_filter: "week",
    },
  },
});

console.log(result.providerMetadata);
// {
//   perplexity: {
//     usage: { citationTokens: 5286, numSearchQueries: 1 },
//     images: [{ imageUrl: "...", originUrl: "...", height: 1280, width: 720 }],
//   },
// }
Any other Perplexity API parameter can be passed the same way.
OptionTypeDescription
return_imagesbooleanInclude images in the response (Tier-2+ accounts).
search_recency_filterstringOne of 'hour', 'day', 'week', 'month'.

​
Custom Provider Configuration

Use createPerplexity when you need a custom base URL, headers, or a custom fetch implementation: 
import { createPerplexity } from "@ai-sdk/perplexity";

const perplexity = createPerplexity({
  apiKey: process.env.PERPLEXITY_API_KEY ?? "",
  baseURL: "https://api.perplexity.ai",
  headers: {
    "X-Pplx-Integration": "my-app/1.0",
  },
});

​
PDF Inputs

Sonar models can read PDF files passed as file message parts: 
import { perplexity } from "@ai-sdk/perplexity";
import { generateText } from "ai";
import fs from "node:fs";

const result = await generateText({
  model: perplexity("sonar-pro"),
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "What is this document about?" },
        {
          type: "file",
          data: fs.readFileSync("./data/ai.pdf"),
          mediaType: "application/pdf",
          filename: "ai.pdf",
        },
      ],
    },
  ],
});
You can also pass a PDF URL: 
{
  type: "file",
  data: new URL("https://example.com/document.pdf"),
  mediaType: "application/pdf",
  filename: "document.pdf",
}

​
Supported Models

ModelImage InputObject Generation
sonarYesYes
sonar-proYesYes
sonar-reasoningYesYes
sonar-reasoning-proYesYes
sonar-deep-researchNoYes
See all available models for full capability details.

​
Streaming and React Hooks

The provider works seamlessly with streamText, useChat, and useCompletion from ai/react. Drop perplexity("sonar-pro") into any AI SDK helper that takes a model: 
import { perplexity } from "@ai-sdk/perplexity";
import { streamText } from "ai";

const result = streamText({
  model: perplexity("sonar"),
  prompt: "Give me a one-sentence summary of this week's AI news.",
});

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

Vercel AI SDK Provider

Official @ai-sdk/perplexity provider docs.

Vercel AI SDK Docs

Full Vercel AI SDK documentation.

Perplexity API Reference

Full Perplexity API parameter reference.

Perplexity Models

Available Sonar models and capabilities.

​
Support

Need help with the integration?