Perplexity Pro gives you access to the latest AI models from OpenAI and Anthropic. Here’s a quick overview of each model currently included—the list evolves as models update.

All models come with context windows of around 32,000 tokens.

Default

Our default model is optimized for speed and web browsing. It’s fine-tuned to deliver fast, accurate answers—perfect for quick searches.

GPT-4 Omni

OpenAI’s latest model for ChatGPT. It has strong reasoning abilities and natural language processing, performing at a human-like level on many professional and academic tasks. It’s impressively fast and works across multiple tasks, making it highly versatile.

Claude 3.5 Sonnet and Claude 3 Opus

Choose between two versions: Claude 3.5 Sonnet, Anthropic’s latest release, and Claude 3 Opus. 3.5 Sonnet is one of the most advanced large language model (LLM) available, particularly excelling at handling nuanced language tasks with a strong balance of speed and accuracy.

Sonar Large

Built on the LlaMa 3.1 70B open-source model, Sonar is trained in-house to work seamlessly with Perplexity’s search engine, making it a perfect fit for our cutting-edge search tech.

How do I choose the right model?

The best way to figure out which model works for you is to test them out. Try comparing your queries across different models and see which one suits your needs best. It all comes down to what you’re looking to achieve.

What’s a token?

A token is a small chunk of text that AI models break down to process. Think of tokens as building blocks that help AI understand and generate language. You can use a tokenizer to see how many tokens a given piece of text contains.

Are there any guidelines for using third-party models like Claude or GPT?

No, you can use these models just as you would in their original platforms.