Questions & Answers

Confidence % is the chair model's estimate of how well-supported each claim is, based on the debate. It reflects model agreement — not an absolute measure of truth.

• 100% — all participating models agreed on this point without needing debate.
• 70–99% — most models agreed, or initial disagreement was resolved during debate.
• Below 70% — significant disagreement remained after all debate rounds.

A high confidence score means the AI models converged — it does not guarantee the claim is factually correct. Always verify important claims independently.

Each Key Claim carries a source label showing how consensus was reached:

• consensus — all models agreed from the very first round, with no debate needed.
• debate_resolved — models initially disagreed, but after one or more debate rounds they converged on the same position.
• disputed — models still disagreed after all debate rounds completed. The positions shown under the claim are each model's final stance.

The Overall Confidence is the chair model's holistic assessment of the entire answer — how much the debating models agreed overall, across all claims. It is a weighted average considering how many claims were disputed vs. agreed, and how fully the debates were resolved.

Consensable runs a four-step process:

• Step 1 — Query: Your question is sent to all selected models simultaneously. Each answers independently.
• Step 2 — Analysis: The chair model reads all responses and identifies points of consensus and disagreement.
• Step 3 — Debate: For each disputed claim, the models engage in structured rounds. Each model sees the others' positions and can update or defend its own. Disputes run in parallel.
• Step 4 — Synthesis: The chair model produces a final synthesised answer, verdict, confidence scores, and key claims.

These are safety caps that prevent the debate from running too long or costing too much:

• Max Rounds — the maximum number of debate rounds per disputed claim. Each round, every model gets one response.
• Max Tokens — the total token budget across all model calls. The debate stops early if this limit is hit.
• Max Minutes — a wall-clock time limit. Useful for keeping responses fast on time-sensitive topics.

Synthesis always runs to completion regardless of caps — only the debate phase is cut short.

The Chair is the model that facilitates the debate, analyses consensus and disagreements, and produces the final synthesised answer. It does not participate in the initial debate itself — it acts as a neutral moderator and synthesiser. You can choose which model acts as chair from the models you've selected.

For questions about recent events, current news, or real-time data, the models' training data may be out of date. Live Web Context fetches fresh information from the web and injects it into all model prompts:

• Auto — a cheap classifier model first decides whether the question needs web search. If yes, Brave Search is used; if not, the web search is skipped.
• Brave — always searches via Brave Search, returning the top 6 results.
• Perplexity — uses Perplexity's AI-powered search to produce a pre-summarised web context.
• None — no web search; models rely entirely on their training data.

Costs are based on the number of tokens (units of text) processed by each AI model. Each model has a different per-token price. The cost shown is the total across all model calls during your query, including the debate and synthesis steps.

The initial cost shown (marked ~) is a real-time estimate based on token counts. The final actual cost is confirmed a few seconds later from the model provider and updates automatically.

Longer questions, more complex topics with more disputed claims, more debate rounds, and larger max-token budgets all increase cost. Using larger or premium models (like Claude Opus or GPT-5) also increases cost compared to faster mid-tier models.