Typesafe AI opens Jev model as Monad engineer builds 300-millisecond onchain trading bot

Typesafe AI opens Jev model as Monad engineer builds 300-millisecond onchain trading bot

N
News Editor
2026-09-22 02:30:14
Typesafe AI has opened access to Jev, its System One model, scrapping the waitlist and giving each new user $5 in credits. According to Bitcoin.com News, the model was developed in secret for two years and has raised $40 million in funding. Jev is not built for chat. It only accepts facts and closed-ended questions, then returns probability-based outputs in 70 to 500 milliseconds. Pricing is set at $0.042 per 1 million input tokens, while output is free. The report also highlighted an early trading use case. In a Bitcoin price test, Jev estimated a 55% chance that Binance 1-minute candles would hit $85,000 before 2027, with probabilities of 48% for $90,000 and 34% for $100,000. The corresponding market-implied probability on Polymarket for $85,000 stood at 81%. On Sept. 16, Monad chief AI engineer Jarrod Watts connected Jev to price feeds and built a trading bot that submits limit orders on the Kuru onchain order book about every 300 milliseconds. The bot can buy or sell based on Jev’s output, and the code has been released on GitHub under jarrodwatts/jev-trader.

Typesafe AI has opened access to Jev, its System One model, removed the waitlist, and is offering $5 in credits to each new user.

According to Bitcoin.com News, the project was developed in secret for two years and has raised $40 million. Jev is not a chat model. It only takes facts and closed-ended questions, then returns probability outputs in 70 to 500 milliseconds. Input pricing is $0.042 per 1 million tokens, while output is free. It can answer questions framed as buy or sell, or yes or no.

Bitcoin price test figures

In a Bitcoin forecasting test, Jev put the probability that Binance 1-minute candles reach $85,000 before 2027 at 55%. The probabilities for $90,000 and $100,000 were 48% and 34%, respectively. Polymarket showed a corresponding market probability of 81% for the $85,000 level.

Monad engineer puts Jev into an onchain trading bot

On Sept. 16, Monad chief AI engineer Jarrod Watts connected Jev to price data and built a trading bot that submits limit orders to the Kuru onchain order book about every 300 milliseconds. The bot can place buy or sell decisions based on Jev’s output.

The bot has been open-sourced on GitHub under the repository name jarrodwatts/jev-trader.

This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan.
200

Disclaimer:

The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.

Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.