What AI models are available in Perplexity?
Perplexity offers eight AI models as of December 2025:
Best (default),
Sonar,
Claude Opus 4.5,
Claude Sonnet 4.5,
Grok 4.1, and
Kimi K2 Thinking.
Free users access the "Best" mode, which automatically selects an optimized model for quick, accurate answers. Pro subscribers unlock manual model selection, allowing them to choose from cutting-edge options like OpenAI's GPT-5.1 for complex reasoning, Anthropic's Claude Opus 4.5 for detailed analysis, or Google's Gemini 3 Pro for multimodal tasks. The Sonar model represents Perplexity's proprietary technology, designed explicitly for search-grounded responses with real-time citations.
What AI models are available in Perplexity?
Which Perplexity model is best for research?
Research mode with GPT-5.1 or Claude Opus 4.5 delivers the best results for in-depth analysis and comprehensive reports. Research mode conducts deep research on any topic, using up to 10x more sources than standard Search mode, generating structured reports with charts, citations, and advanced reasoning. GPT-5.1 excels at complex multi-step reasoning and synthesis across diverse sources, while Claude Opus 4.5 (marked as "max") provides exceptional detail and nuance in long-form analysis. This mode automatically orchestrates multiple web queries before synthesizing findings, making it ideal for professional research, competitive analysis, or technical documentation needs.
How do I select a different AI model in Perplexity?
Click the model selector icon in the search input box to choose your preferred AI model from the dropdown menu. The icon appears directly in the search bar alongside other tools like file attachments and voice input. Once clicked, you'll see the complete list of available models with indicators showing which are new or premium options. Note that manual model selection is a Pro feature—free users are limited to the "Best" mode that automatically handles model selection. After choosing a model, it remains active for subsequent queries until you manually change it again.
How do I select a different AI model in Perplexity?
What's the difference between Search and Research modes?
Search mode provides fast answers to everyday questions, while Research mode conducts deep, multi-source analysis for complex topics. Search mode optimizes for speed and quick factual responses, perfect for straightforward queries like definitions, current events, or simple comparisons. Research mode takes longer but delivers comprehensive reports with extensive citations, data visualization, and thorough exploration of your topic from multiple angles. Perplexity also offers Labs mode, an experimental feature showcasing advanced capabilities for technical workflows and specialized use cases. Pro users get unlimited Research queries, while free users receive limited access to this premium search experience.
Is Perplexity Pro worth it for model selection?
Perplexity Pro justifies its cost if you regularly need advanced AI capabilities, unlimited research queries, or specific model preferences for professional work. At $20 monthly, Pro unlocks manual selection of premium models like GPT-5.1 and Claude Opus 4.5, unlimited Research mode access, and unlimited file uploads for document analysis. The ability to "choose your model" matters most for power users who understand each model's strengths—GPT-5.1 for reasoning, Claude for long-context analysis, Gemini for multimodal tasks. For casual users satisfied with quick answers, the free tier's Best mode provides excellent results without manual model management.
Dr. Hernani Costa
Founder & CEO of First AI Movers
Looking for more great writing in your inbox? 👉 Discover the newsletters busy professionals love to read.