Model Council is a multi-model research feature that brings several AI models together to provide one comprehensive answer to user queries. Instead of manually verifying queries across multiple models, users can now run the same query across several models simultaneously.

Model Council runs queries across three of the top models available on Perplexity at once, such as Claude Opus 4.6, GPT 5.2, and Gemini 3.0. A synthesizer model reviews the outputs, resolves conflicts where possible, and provides one answer that shows where the models agree and where they differ. The feature builds on Perplexity's advantage of using multiple models, allowing users to query several models at once instead of switching between them individually.

The system works by running the user's query across multiple frontier models simultaneously. A synthesizer model then analyzes all the outputs, resolves conflicts where possible, and delivers a unified response that clearly indicates areas of consensus and disagreement among the different AI models.

Model Council provides higher-confidence answers by highlighting where models converge and where they disagree. It's especially valuable for investment research to get balanced views on stocks and financial decisions, complex decisions like major purchases or career moves, creative brainstorming for gifts or travel plans, and verification when users need to be confident they're getting accurate information.

Model Council is available for Perplexity Max subscribers on the web, with mobile app support coming soon. The feature leverages Perplexity's unique position of offering access to all top AI models and addresses the challenge of model performance variation across different tasks and questions.