LLM·Dex
ProprietaryPerplexitymidtext

Sonar Large

Perplexity's flagship answer-engine model with built-in web search grounding.

Updated


Quick facts

Released
Nov 2024
Context
127K tokens
Output / 1M
$1.00 / 1M tokens
License
Proprietary

About Sonar Large

Sonar Large is the production model behind Perplexity's answer engine. It's not a general-purpose chat model, it's tuned to take a query, search the web, and produce a cited answer. For Q&A with sources it's hard to beat; for everything else use a different model.

Benchmarks

Published scores from Perplexity's model card or independent leaderboards. We do not publish numbers we cannot source, see methodology.

HumanEval
,
Python coding pass@1
MMLU
,
Broad academic knowledge
GPQA
,
Graduate-level reasoning
SWE-bench
,
Real software-engineering tasks
Benchmark scores not yet available. We only publish numbers we can source from official model cards or independent leaderboards, see methodology.

Capabilities

Strengths

  • Web-search grounded
  • Citation-first output
  • Cheap

Tracked weaknesses

  • Not a general-purpose chat model

Pricing

Per-million-token rates as published by Perplexity.

TierPriceNotes
Input$1.00 / 1M tokensTokens you send to the model
Output$1.00 / 1M tokensTokens the model generates
Context127K tokensMax combined input + output

Call Sonar Large from your code

Drop-in snippet for the Perplexity SDK. Set your API key in the environment and run.

typescript
import OpenAI from "openai";

const client = new OpenAI({
  // Use OPENAI_API_KEY for OpenAI, or your provider's key + baseURL.
  apiKey: process.env.OPENAI_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "sonar-large",
  messages: [
    { role: "user", content: "What's the time complexity of quicksort?" },
  ],
});

console.log(completion.choices[0].message.content);

Compare Sonar Large with…

Frequently asked

  • How much does Sonar Large cost per million tokens?
    Sonar Large is priced at $1.00 / 1M tokens for input tokens and $1.00 / 1M tokens for output tokens via the official Perplexity API at the time of writing.
  • What is Sonar Large's context window?
    Sonar Large supports a context window of 127K tokens.
  • Is Sonar Large open source?
    No. Sonar Large is a closed-weight model, you can use it via Perplexity's API but the model weights are not publicly downloadable.
  • When was Sonar Large released?
    Sonar Large was released on Nov 19, 2024 by Perplexity.
Friday digest

Intelligence, distilled weekly.

One short email every Friday, new model launches, leaderboard moves, and pricing drops. Curated by hand. Free, no spam.