Can an AI agent beat Kalshi's NYC high temperature market?
A Kalshi NYC high temperature bot that buys the bottom bracket of tomorrow's Central Park ladder when the forecast already sits in it, run on paper against the live order book at Kalshi's fees, with every settled bet on this page.
Every day Kalshi lists a ladder of temperature brackets for NYC (KXHIGHNY), and exactly one wins: which bracket of the day's ladder holds the maximum temperature recorded at New York City (CLINYC), as The Weather Company reports it? 67 of those days settled from Aug 24, 2026 to Oct 29, 2026.
If a rule has an edge on NYC's daily temperatures, an agent trading it on paper against the live KXHIGHNY book at Kalshi's real fees should make money. If it loses, the rule is wrong, however good it sounds. The settled record is the test, and this page is the record.
This is not investment advice. The agent below trades paper contracts, five at a time; its positions exist to benchmark one rule on KXHIGHNY, not to recommend it.
From a rule to a record
A backtest of a NYC temperature rule tells you what it would have done against prices already known. This page wants the other thing: how the idea that the evening ladder starts Central Park too warm fares against the KXHIGHNY book as it stands, each day at 8:00 PM Eastern, filled at the ask, charged Kalshi's fee (about 1.7¢ a contract at 40¢), and settled when the CLINYC report says so. So the NYC agent runs on Windmill like any user's agent, and each bet it places on KXHIGHNY is written here as it settles, wins and losses alike.
How the agent works
The agent is the rule below in plain English, on Claude Haiku 5.5, scheduled once a day, at 8:00 PM Eastern. It builds its record in four steps.
1. Read the station
Every day at 8:00 PM Eastern, it reads tomorrow's daytime high from the NWS forecast for Central Park (api.weather.gov/gridpoints/OKX/34,45/forecast), then reads tomorrow's KXHIGHNY ladder, bracket by bracket, with the live ask on each. A KXHIGHNY day in the facts below had 6 brackets, listed about 39 hours before the ladder closes at 1:00 AM Eastern time.
2. Filter for the setup
It places nothing unless both of these hold:
- that high falls inside the lowest bracket ("X° or below")
- that bracket asks 20–60¢
Why this setup: On 18 of the 67 Central Park days below, the winning bracket was the open-ended one at the bottom of the ladder; the rule buys it the evening before, and only when the NWS forecast for tomorrow already falls inside it.
3. Size and place
It buys 5 YES on it at the ask, on paper against the live KXHIGHNY book: a paper order fills only against what the book shows at that price. At about 40¢ a contract, Kalshi's taker fee at KXHIGHNY's settings (fee type "quadratic", multiplier 1) is about 1.7¢; the 40–59¢ favorites in the price table below paid 1.7¢ on average. So the five contracts cost about $2.08 all in, and pay $5.00 if they win.
4. Hold to settlement and record it
Every position is held until Kalshi settles the day on Central Park's official reading, the National Weather Service report CLINYC as The Weather Company reports it, a median 6.2 hours after the ladder closes. The price paid, the fee, the result and the net go into the record below as each bet settles. Most of the daily runs end with no order, and the agent's log keeps those too.
The record: October 30, 2026
Started October 29, 2026; no settled bets yet.
| Metric | Value |
|---|---|
| Started | Oct 29, 2026, 11:38 PM EDT |
| Bets settled | 0 |
| Bets open | 0 |
| Contracts | 0 |
| Won | 0 |
| Net after fees | — |
| Per contract | — |
Nothing is read into the record before thirty settled bets.
It runs this page's starter rule, word for word:
“Every day at 8:00 PM Eastern, read tomorrow's daytime high from the NWS forecast for Central Park (api.weather.gov/gridpoints/OKX/34,45/forecast); on tomorrow's KXHIGHNY market, if that high falls inside the lowest bracket ("X° or below") and that bracket asks 20–60¢, buy 5 YES on it at the ask. Otherwise no order. Hold to settlement.”
The market the rule is betting into
Kalshi's API listed 67 settled NYC days, from Aug 24, 2026 to Oct 29, 2026: 402 brackets, 6 a day in the median, of which 67 won. The official highs ran from 57°F (Sun, Oct 18) to 84°F (Thu, Sep 10), with a median of 71°F, and on 18 of the 67 days the winner was one of the two open-ended brackets at the ends of the ladder. A median day traded 168,939 contracts across its brackets over the last 7 days.
Each day's ladder was listed about 39 hours before it closed, closed at 1:00 AM Eastern time after the day it is about, and settled a median 6.2 hours after the close, once the official reading was in. Trading runs through the afternoon, while the high is still being set: a rule that buys late in the day knows more, and pays for it in the price.
NYC's official highs
The ten newest days:
| Day | Official high | Winning bracket | Brackets | Contracts traded |
|---|---|---|---|---|
| Wed, Oct 28 | 61°F | 60° to 61° | 6 | 138,248 |
| Tue, Oct 27 | 61°F | 60° to 61° | 6 | 173,260 |
| Mon, Oct 26 | 69°F | 68° to 69° | 6 | 212,248 |
| Sun, Oct 25 | 64°F | 64° to 65° | 6 | 148,843 |
| Sat, Oct 24 | 60°F | 59° to 60° | 6 | 168,939 |
| Fri, Oct 23 | 59°F | 59° to 60° | 6 | 158,899 |
| Thu, Oct 22 | 67°F | 67° to 68° | 6 | 232,213 |
| Wed, Oct 21 | 62°F | 61° to 62° | 6 | 141,795 |
| Tue, Oct 20 | 67°F | 67° to 68° | 6 | 223,092 |
| Mon, Oct 19 | 62°F | 62° to 63° | 6 | 231,353 |
The daily low (KXLOWTNYC)
Kalshi also lists NYC's daily low as its own series, KXLOWTNYC, on the same station. It settled 67 days from Sun, Aug 23 to Wed, Oct 28, with official lows from 41°F to 71°F. A low is often set in the early morning, so its ladder is a different question from the high's, on the same report.
| Day | Official low | Winning bracket | Brackets | Contracts traded |
|---|---|---|---|---|
| Wed, Oct 28 | 45°F | 45° to 46° | 6 | 24,500 |
| Tue, Oct 27 | 46°F | 45° to 46° | 6 | 39,518 |
| Mon, Oct 26 | 50°F | 50° to 51° | 6 | 45,474 |
| Sun, Oct 25 | 43°F | 42° to 43° | 6 | 23,811 |
| Sat, Oct 24 | 44°F | 43° to 44° | 6 | 34,713 |
| Fri, Oct 23 | 47°F | 47° to 48° | 6 | 36,052 |
| Thu, Oct 22 | 49°F | 49° to 50° | 6 | 55,427 |
| Wed, Oct 21 | 50°F | 50° to 51° | 6 | 26,223 |
| Tue, Oct 20 | 50°F | 50° to 51° | 6 | 18,227 |
| Mon, Oct 19 | 47°F | 46° to 47° | 6 | 15,843 |
How the 1 PM favorite did
For each of the 48 newest days up to Oct 29, 2026, we read Kalshi's quote 12 hours before the close and took the favorite, the bracket priced highest, at its ask. 48 had a quote at that moment, and the favorite won 35 of them. Breakeven is the price plus Kalshi's taker fee, as a share of the $1 a winning contract pays.
| Favorite's price | Days | Won | Win rate | 95% range | Breakeven after fee | Read |
|---|---|---|---|---|---|---|
| 40–59¢ | 11 | 6 | 55% | 28%–79% | 56.3% | inside noise |
| 60–79¢ | 22 | 16 | 73% | 52%–87% | 71.3% | inside noise |
| 80–99¢ | 15 | 13 | 87% | 62%–96% | 88.8% | inside noise |
Three notes on that table. The 60–79¢ band has the widest gap between win rate and breakeven, 73% against 71.3%, and at 22 days its interval runs from 52% to 87%, which includes breakeven. Two of the three bands fell short of breakeven, the 80–99¢ band by the most: 87% against 88.8%, where at an average 88.1¢ one loss costs what 8 wins earn. And every band's interval includes breakeven, which is why the last column reads the same three times. In our read of Kalshi's prices, the NYC favorite 12 hours before the close is priced about right. Nothing on this page says a buyer of the favorite has an edge.
The rule under test pays 20–60¢ a contract, which puts it in the 40–59¢ and 60–79¢ rows: there the favorite won 22 of 33 days, against breakevens of 56.3% and 71.3%. The rule's own conditions are what the record above tests; these rows are only the market's baseline at its price.
Kalshi's rules, in Kalshi's words
This is the rule of the market that was open (KXHIGHNY-26OCT30-T76) when we read Kalshi's API on October 30, 2026, quoted from Kalshi; the series and its full rules are on Kalshi's site. The day and the bracket's bounds change with every market:
“If the maximum temperature recorded at New York City (CLINYC) for Oct 30, 2026, is greater than 76° fahrenheit according to The Weather Company, then the market resolves to Yes.”
Kalshi adds, in the same market's rules:
“Not all weather data is the same. While checking a source like AccuWeather or Google Weather may help guide your decision, the official and final value used to determine this market is the maximum/minimum temperature as reported by the Weather Company.”
The series names The Weather Company as its settlement source. Kalshi lists the series with the fee type "quadratic" at a multiplier of 1: a taker pays 1.8¢ a contract at 50¢ before rounding, less toward either end, and a resting order that fills later pays nothing. The fee calculator works out the fee and the breakeven for any price.
The rules name the station "New York City (CLINYC)", and the National Weather Service report behind it is headed "The Central Park NY climate summary": the market settles on the Central Park station (KNYC), not on LaGuardia, JFK or Newark. (NWS New York, climate report CLINYC, checked October 30, 2026.)
What success looks like
A positive net per contract after Kalshi's fees over thirty settled bets, with the confidence interval clear of zero, would be a result.
A rule that only matches its price is not one. A contract bought near 40¢ that wins as often as that price says, 40 times in a hundred, loses about 1.7¢ a contract to the fee alone (the 40–59¢ favorites in the price table paid 1.7¢), so the line to beat on KXHIGHNY is a win rate of about 41.7%, not 40%. Each win at that price nets about 58.3¢ a contract after the fee and each loss costs 41.7¢, so one win covers 1.4 losses.
The rule runs once a day, so thirty settled bets take at least 30 days, and longer when the setup is rare. If the record climbs, the idea that the evening ladder starts Central Park too warm holds at these prices. If it falls, the idea goes, and the record stays on this page.
Follow along
- This page refreshes every hour from Kalshi's settled data and the agent's own log.
- Copy the NYC agent: the button below opens the builder with this KXHIGHNY rule, to run as written on paper under your own account, or with your own numbers in place of 20–60¢.
- The fee calculator shows the fee and the breakeven at any price on KXHIGHNY.
- The 90-strategy test is the longer version of this exercise: about 90 rules and 4,200 paper bets across ten days.
- The Kalshi markets hub lists the other weather cities and every other market page.
Questions
- What does Kalshi's NYC high temperature market settle on?
- On the day's maximum temperature at Central Park, as The Weather Company reports it; the rules name the station NYC report (CLINYC). Exactly one bracket of the day's ladder wins.
- What is the fee at 50¢?
- A taker pays 1.8¢ a contract before rounding at 50¢ on this series (fee type "quadratic", multiplier 1), less toward either end. The fee calculator gives the fee and breakeven at any price.
- Is a bot here profitable?
- Nothing on this page says so. The favorite 12 hours before the close won 35 of 48 days in our read of Kalshi's prices, and the table shows each price band against its breakeven: 3 of its 3 bands are inside noise. Run your own rule on paper to see what it does, before you risk money.
- Paper or live?
- Agents trade on paper unless you build them live. Paper orders fill against Kalshi's live order book with Kalshi's fees and settle when the real market settles. To trade real money, connect your own Kalshi API key and build a live agent; your money stays on your Kalshi account.
Other market pages: Los Angeles · Austin · Denver · Philadelphia · San Francisco · Miami · Chicago · all Kalshi markets