Perplexity: Llama 3.1 Sonar 70B

perplexity/llama-3.1-sonar-large-128k-chat

Created Aug 1131,072 context

$1/M input tokens$1/M output tokens

Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance.

This is a normal offline LLM, but the online version of this model has Internet access.

Providers for Llama 3.1 Sonar 70B

OpenRouter load-balances requests across providers weighted by price unless you use dynamic routing.

Apps using Llama 3.1 Sonar 70B

Top public apps this week using this model

Recent activity on Llama 3.1 Sonar 70B

Tokens processed per day

Uptime stats for Llama 3.1 Sonar 70B

Uptime stats for Llama 3.1 Sonar 70B across all providers

Sample code and API for Llama 3.1 Sonar 70B

OpenRouter normalizes requests and responses across providers for you.

To get started, you can use Llama 3.1 Sonar 70B via API like this:

fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${OPENROUTER_API_KEY}`,
    "HTTP-Referer": `${YOUR_SITE_URL}`, // Optional, for including your app on openrouter.ai rankings.
    "X-Title": `${YOUR_SITE_NAME}`, // Optional. Shows in rankings on openrouter.ai.
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "perplexity/llama-3.1-sonar-large-128k-chat",
    "messages": [
      {
        "role": "user",
        "content": "What is the meaning of life?"
      }
    ]
  })
});

You can also use OpenRouter with OpenAI's client API:

import OpenAI from "openai"

const openai = new OpenAI({
  baseURL: "https://openrouter.ai/api/v1",
  apiKey: $OPENROUTER_API_KEY,
  defaultHeaders: {
    "HTTP-Referer": $YOUR_SITE_URL, // Optional, for including your app on openrouter.ai rankings.
    "X-Title": $YOUR_SITE_NAME, // Optional. Shows in rankings on openrouter.ai.
  }
})

async function main() {
  const completion = await openai.chat.completions.create({
    model: "perplexity/llama-3.1-sonar-large-128k-chat",
    messages: [
      {
        "role": "user",
        "content": "What is the meaning of life?"
      }
    ]
  })

  console.log(completion.choices[0].message)
}
main()

See the Request docs for all possible parameters, and Parameters for recommended values.