LLaMA 3.1 Sonar Small 128k Online
by
Perplexity
Model ID:
llama-3.1-sonar-small-128k-online
Overview
LLaMA 3.1 Sonar Small 128k Online is a smaller variant of the Sonar model, also optimized for online applications with a 128,000 token context. It offers a balance between performance and efficiency, making it suitable for applications that require rapid responses without compromising on quality.
Specializations
Online accessibility: This model is readily available online, making it convenient for quick interactions and real-time applications.
Compact size: With a smaller size, it offers a good balance between performance and resource efficiency, suitable for less demanding tasks.
Focused on factual responses: It excels at providing accurate and informative answers based on real-world knowledge.
Integration Guide (Javascript)
To use this model through Portkey, follow these steps:
1. Install Portkey SDK:
npm install --save portkey-ai
2. Set up client with Portkey:
import Portkey from 'portkey-ai'
const portkey = new Portkey({
apiKey: "PORTKEY_API_KEY",
virtualKey: "VIRTUAL_KEY" // Your Perplexity AI Virtual Key
})
3. Make a request:
const chatCompletion = await portkey.chat.completions.create({
messages: [{ role: 'user', content: 'Say this is a test' }],
model: 'llama-3-1-sonar-small-128k-online',
})
console.log(chatCompletion.choices[0].message.content);
Model Specifications
Release Date:
12/2/2024
Max. Context Tokens:
128K
Model Size
8B
License:
Open-Source
Pricing
$/Million Input Tokens
$
0.2
$/Million Output Tokens
$
0.2
Live updates via Portkey Pricing API. Coming Soon...
© 2024 Portkey, Inc. All rights reserved