Perplexity: Llama 3.1 Sonar 8B Online

Text input Text output Unavailable
Author's Description

Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance. This is the online version of the [offline chat model](/models/perplexity/llama-3.1-sonar-small-128k-chat). It is focused on delivering helpful, up-to-date, and factual responses. #online

Key Specifications
Cost
$$
Context
127K
Parameters
8B
Released
Jul 31, 2024
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Top P Frequency Penalty Max Tokens Presence Penalty Temperature
Performance Summary

Perplexity: Llama 3.1 Sonar 8B Online, released on July 31, 2024, is Perplexity's latest online model, designed for helpful, up-to-date, and factual responses. This model consistently ranks among the fastest and most competitively priced, achieving an "Infinityth percentile" across five benchmarks for both speed and cost efficiency. In terms of performance across specific benchmarks, the model demonstrates a notable strength in Reasoning, achieving 74.0% accuracy (73rd percentile), indicating strong logical and problem-solving capabilities. However, its performance in other areas is less consistent. Coding (Baseline) shows a modest 24.0% accuracy (21st percentile), while Email Classification (Baseline) is lower at 81.0% accuracy (10th percentile). A significant weakness is observed in Ethics (Baseline), with a very low 4.0% accuracy (8th percentile), and General Knowledge (Baseline) where it scored 0.0% accuracy. The model's reliability is not explicitly provided in percentile terms, but the duration metrics suggest it consistently provides responses, albeit with varying accuracy. Overall, while excelling in speed, cost, and reasoning, the model exhibits considerable room for improvement in specialized knowledge domains like ethics and general knowledge.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.2
Completion $0.2
Request $0.005 per request

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Perplexity
Perplexity | perplexity/llama-3.1-sonar-small-128k-online 127K $0.2 / 1M tokens $0.2 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Free Executions Accuracy Cost Duration
Other Models by perplexity