Vi: ask a question from inside the market you are researching

The useful version of an assistant here is not one that has opinions about crypto. It is one that is already looking at the market you have open, can be asked a specific question about it, and shows you what it read. Vi is available from the crypto and prediction workspaces, with a monthly message allowance by plan.

Published research source index

The published research documents Vi and this site draw on, with their publication and revision dates.

No source observation time · Published

Public research documents that can be read directly or retrieved through Vultax’s existing research exports and MCP endpoint.
ResearchPublishedRevised
How Polymarket Settles: 110,576 Markets, a Median of 2.2 Hours, and 89 Disputes2026-09-172026-09-18
Liquidity Rewards: Polymarket Offers $150,000 a Day; Kalshi Paid $2.95M in 30 Days2026-09-172026-09-17
Kalshi–Polymarket Arbitrage: 32,638 Price Checks, and Where a Gap Survived Fees2026-09-162026-09-16
Polymarket vs Kalshi Midterm Odds: 65 Matched Contracts and What a $50,000 Bet Moves2026-09-162026-09-16
Polymarket's Up-or-Down Crypto Markets: 60% of Its Trades, Priced About Right, 1.6% Fee2026-09-152026-09-16
Why Bitcoin's Price Differs Between Exchanges: 18 Venues Checked Every Minute2026-09-142026-09-16
Where the Money Waits: Polymarket's Open Interest Is 55% Politics, Kalshi's 44% Sports2026-09-132026-09-16
Polymarket Copy Trading: Following 30 Seconds Late Cost 1.43¢ a Share, Before Fees2026-09-122026-09-16

What you can do with it

Ask from the market, not from a blank box

Open the pair or the contract first and ask from there. A question tied to a specific market and a specific observation gets an answer you can check; a question asked in the abstract gets an essay.

Ask what the data does not show

The most productive questions are about coverage and limits: which venues are in this figure, how old is it, what population does this rank describe. Those have definite answers, and they are the answers that stop a mistake.

Check the answer against the table

Every figure Vi discusses exists somewhere on a page with a source time attached. A fluent answer is not evidence that a source was current, and the tables are where that gets settled.

Read the published research directly

The research documents behind the assistant are public, dated and exportable. Where a question has already been studied properly, the study is a better answer than a conversation.

How it works

Context, then question

Vi is reached from within a workspace, so the market you are on is part of the question. That is the difference between an assistant that can be checked and a chat window that happens to be on a finance site.

Conversations are tied to your account. They are not used to train anyone's model, ours or a provider's, and the privacy policy states what is kept and for how long.

What an assistant is bad at

Anything that requires knowing whether a number is current. A language model will produce a confident sentence about a stale figure exactly as readily as about a fresh one, which is why every surface on Vultax carries its own observation time and why the honest instruction is to check the table.

It is also not a forecaster. Vi does not estimate the probability of an event on your behalf, and an answer that sounds like a prediction should be read as a summary of what was asked for, not as a view Vultax holds.

Limits and allowances

Vi sits on Essential and above with a monthly message allowance that rises with the plan; the allowance for each is in the plan table on this page and in the price list. Your account's current usage and remaining messages are shown in Settings.

Questions that get useful answers

Ask about scope. Which venues are in this figure, what window does it cover, what population does this rank describe. These have definite answers, they are the answers that prevent mistakes, and they are exactly what a general chat assistant cannot give you about a specific table.

Ask about disagreement. Where two views on the same market differ, asking why usually surfaces a difference in window or population rather than a contradiction, and that is worth knowing before you act on either.

Do not ask what will happen. Nothing in the product estimates the probability of an event on your behalf, and an answer shaped like a forecast is a summary of the question rather than a view Vultax holds.

What each plan gives you here

What a plan changes on this surface.

Vi Assistant availability by plan
What you getFreeEssentialPremiumPro
Vi assistant, with a monthly message allowanceNot included1,000 a month3,000 a month5,000 a month
Prediction market prices, charts and market pagesIncludedIncludedIncludedIncluded
Crypto prices, order books and depthIncludedIncludedIncludedIncluded

Full plan comparison and prices · Refer & earn 30%

Compared with a general AI chat

A general assistant can discuss prediction markets fluently and cannot tell you what the book looked like a minute ago. The narrow advantage here is proximity to dated data and to the published research, and the honest limitation is the same one every language model has: it will not know when it is out of date unless something on the page tells it.

Competitor details last checked . They describe other products as their operators published them, not as an assessment of them.

The table in full

Each table carries its own source, observation time, coverage and limits, and can be taken away as JSON or CSV. A missing value means the source did not report it; it is never rendered as a zero.

01 Source index

Published research source index

Public research documents that can be read directly or retrieved through Vultax’s existing research exports and MCP endpoint.

PublishedPublication updated 19 rowsOnly published, indexable research appears here; each document has its own observation window.

Published research source index. Vultax’s currently published research catalogue. This is a document index, not a live quote feed or a record of Vi answers.
ResearchPublishedRevised
How Polymarket Settles: 110,576 Markets, a Median of 2.2 Hours, and 89 Disputes2026-09-172026-09-18
Liquidity Rewards: Polymarket Offers $150,000 a Day; Kalshi Paid $2.95M in 30 Days2026-09-172026-09-17
Kalshi–Polymarket Arbitrage: 32,638 Price Checks, and Where a Gap Survived Fees2026-09-162026-09-16
Polymarket vs Kalshi Midterm Odds: 65 Matched Contracts and What a $50,000 Bet Moves2026-09-162026-09-16
Polymarket's Up-or-Down Crypto Markets: 60% of Its Trades, Priced About Right, 1.6% Fee2026-09-152026-09-16
Why Bitcoin's Price Differs Between Exchanges: 18 Venues Checked Every Minute2026-09-142026-09-16
Where the Money Waits: Polymarket's Open Interest Is 55% Politics, Kalshi's 44% Sports2026-09-132026-09-16
Polymarket Copy Trading: Following 30 Seconds Late Cost 1.43¢ a Share, Before Fees2026-09-122026-09-16
Best Polymarket Traders: 36 Wallets Took 44% of Gains, and Active Winners Kept Winning2026-09-112026-09-16
Best Polymarket Tools and Whale Trackers in 2026: 22 Compared, 4 Publish Their Latency2026-09-072026-09-16
Fed Decision Odds, Scored: Polymarket vs Kalshi at Every 2026 FOMC Meeting2026-09-062026-09-16
Polymarket Sports and Esports: Esports Took 21.4% of the Money on the Thinnest Books2026-09-062026-09-16
115,006 Large-Trade Alerts: Where and When Crypto Whales Trade, by Venue and Hour2026-09-032026-09-16
Crypto Exchange Feed Latency and Coverage: 16 Venues Measured2026-09-022026-09-16
Crypto Wash Trading and Real Liquidity: Fake-Volume Estimates Run From 51% to 95%2026-09-022026-09-16
Is Polymarket Legal in the US? Where Prediction Markets Stand in September 20262026-09-142026-09-14
1.6% of Polymarket Wallets Never Sleep. They Made 58% of All Trades.2026-09-092026-09-09
We Tested Polymarket Prices Against 6,776 Resolved Markets. Here's Where They Bend.2026-09-082026-09-08
Order-Book Spoofing: What It Looks Like in Live Data2026-09-022026-09-07

CoverageVultax’s currently published research catalogue. This is a document index, not a live quote feed or a record of Vi answers.

Research observation dates and publication dates are distinct. Follow the document to its methodology and source data.

SourcesVultax public research access

Questions

Which plan includes Vi?

Essential and above, each with a monthly message allowance. The plan table on this page is generated from the same entitlement map as the price list.

Does Vi trade for me?

No. There is no execution anywhere in Vultax, on any plan. Vi answers questions about market data.

Are my conversations used for training?

No. Vi conversations are not used to train anyone's model. The privacy policy sets out retention.

Can Vi be wrong?

Yes. AI output can be incomplete or mistaken, and fluency is not accuracy. Check anything material against the table it came from.

What happens when I reach the allowance?

Requests are declined for the rest of the plan window with a quota message, and Settings shows what is left before you get there.

Can Vi read my positions?

Vi works with market data and the research catalogue. Account data is not used for market research or shared into published figures.

Coverage and methodology

  • Public tables mirror existing Vultax source packs. They do not include account data, private watchlists or the complete app dataset.
  • Source time, coverage and limitations apply to each table. Missing values are unavailable, not zero.

Methodology

Take this into the workspace

The research catalogue below is public. Essential and above add Vi inside the app, with a monthly message allowance.

A free account needs no payment card and starts no subscription. JSON · Markdown · Schema