Perplexity’s tokenmaxxing Model Council gives you multiple bot perspectives
Perplexity has expanded its "Model Council" feature to its cloud-based Computer platform, letting users query multiple AI models simultaneously and receive a synthesised report highlighting where their answers agree or diverge. The move matters because it gives paying customers more flexibility for tackling ambiguous, judgement-heavy questions—such as legal, financial or business-strategy queries—by comparing perspectives from several frontier and open-weight models rather than relying on a single AI's answer.
Previously restricted to three fixed models with no user input, Model Council now lets users select between two and eight models, drawn from providers including OpenAI, Anthropic and Google, as well as open-weight options like GLM and Kimi. An orchestrator model runs each chosen model as an independent subagent, then a user-selected "chair" model synthesises the results into a report, which Computer can further convert into documents such as board decks. The feature, previously limited to Max ($200/month) and enterprise subscribers, is now also available to Pro users paying $20 a month.
- Perplexity brings multi-model "Model Council" feature to its Computer platform
- Users can pick 2-8 AI models to compare answers on one query
- Feature now available to $20/month Pro subscribers, not just Max/enterprise tiers