Perplexity Expands Model Council to Computer Platform
AI search firm Perplexity has extended its Model Council feature to its cloud-based Computer platform, giving users more ways to configure multi-model queries. The expansion, announced Tuesday, builds on the five-month-old Model Council that was previously limited to Perplexity's own interface.
The Model Council is designed to "allow users to build a board of top models for a single issue," Perplexity said in its release. When assigned to a council and given a prompt, models tackle the problem independently. The system then produces a synthesis report that explains where their conclusions agree and diverge.
According to Perplexity communications chief Jesse Dwyer, Model Council functions as a skill that tells an orchestrator model to spin up parallel subagents. Each subagent acts as a full agent harness and tackles the problem independently.
"A wait barrier holds until every perspective finishes, then the model the user selected acts as the 'chair,'" Dwyer told The Register in an email. "It reads all the perspective outputs and synthesizes them, explicitly surfacing where the models agree and where they diverge."
From Three Models to Eight
When originally launched in February, the Model Council was restricted to three models available on Perplexity with no user choice. Users would ask a query and get an answer put together by a synthesizer model from whichever models were available at the time.
With the addition of Model Council to Computer, users can now choose from two to eight models for their AI advisory board. Options range from models supplied by frontier labs such as OpenAI, Anthropic, and Google to open-weight models including GLM and Kimi. Analysis depth can also be customized. While a synthesizer model still puts together the report, Computer can also "turn that synthesis into outputs like reports, board decks, and other work-ready assets," Perplexity said.
Computer, for those unfamiliar with it, is essentially a web interface for a model orchestration layer.
Ideal for Ambiguous Questions
Perplexity describes the overhauled and expanded Model Council as being ideal for ambiguous questions involving "judgment calls, tradeoffs, assessing risks or other situations where there's no one right answer." The company said model-to-model dialogue "shows where there's consensus and where there's conflict."
Stay ahead of the AI curve
The most important updates, news, and content — delivered weekly.
No spam. Unsubscribe anytime.
"Consensus gives people more confidence to move forward," the company said. "Gaps show them where to go deeper."
Model Council has a number of intended use cases, Perplexity said, including legal questions, financial queries, corporate decision making, business growth modeling, and even engineering. Being added to Computer makes it even more useful, apparently, because users can now ask it for additional details to "sharpen the answer" and ask pointed follow-up questions to get a stronger result.
Perplexity also encourages users to ask the Council for confidence levels to see what different models think of their collective answer. "Disagreements often come from different starting assumptions, so ask each model to state the assumptions behind its conclusions."
Pricing and Credits
Access to Model Council was previously restricted to enterprise tiers, either $34 per month per seat for Pro or $271 for Max, and individual Max ($200 per month) customers. With the expansion into Computer, the Council will now serve individual Max and Pro ($20 per month) users, as well as those on enterprise tiers.
But that is not the only cost associated with the reformed Model Council, because Computer relies on usage-based billing. Pro users get an initial pool of 4,000 bonus credits, while Max customers get 35,000 and a renewing 10,000 a month. Enterprise Pro customers get 8,000 bonus credits and 500 a month per seat, while Enterprise Max customers start with a 45,000 bonus pool and get 15,000 per seat per month.
According to Perplexity, 100 Computer credits are equal to $1. A "light" task, like summarizing a document and pulling out key points, can eat between 100 and 350 credits. A "heavy" task, which Perplexity describes as creating work-ready assets like pitch decks, can eat as many as 2,275 credits. Because Computer credits function at the product level rather than mapping directly to raw AI token usage, it is not clear how many credits a Model Council session could burn, and Perplexity did not get specific.
In other words, if you want the Council to weigh in on one of those aforementioned ambiguous questions, it could cost you. AI tokens can get quite expensive, after all.
"Query complexity will affect token usage more than the specific model selection," Dwyer explained. "Simple queries in Computer can cost less than a penny while complex tasks run higher."