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:

Max Tokens Top P Frequency Penalty Temperature Presence Penalty
Performance Summary

Perplexity: Llama 3.1 Sonar 8B Online, released on July 31, 2024, demonstrates exceptional speed and cost-efficiency. It consistently ranks among the fastest models and offers highly competitive pricing across all evaluated benchmarks. This online version of the Llama 3.1 Sonar family is designed for delivering up-to-date and factual responses. In terms of performance across categories, the model shows varied capabilities. It achieved a notable 81.0% accuracy in Email Classification, indicating a strong ability to understand context and purpose in text, though this places it in the 9th percentile for accuracy in this specific benchmark. However, its performance in other areas is significantly lower. It scored 24.0% in Coding and a very low 4.0% in Ethics, placing it in the 18th and 7th percentiles respectively. The General Knowledge benchmark yielded 0.0% accuracy, suggesting a significant limitation in its ability to answer a broad range of knowledge-based questions in this specific test format. While its speed and cost are outstanding, the model's accuracy across several critical benchmarks, particularly General Knowledge and Ethics, indicates substantial areas for improvement in its factual recall and ethical reasoning capabilities.

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 Strategy Free Executions Accuracy Cost Duration
Other Models by perplexity